© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129223
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric expressions—especially measurements or dosages often shown with digits and decimal points.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    medical conditions or problems

    np_acts-logits-general · gemini-2.5-flash-lite

    medical conditions and symptoms described in clinical or academic medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.34
     décisions
    -1.26
    瞟
    -1.24
    看了一眼
    -1.20
     пользователей
    -1.19
     brillant
    -1.13
    :
    -1.11
    笵
    -1.09
     ſol
    -1.09
     instead
    -1.09
    POSITIVE LOGITS
     any
    1.77
     particularly
    1.56
     including
    1.53
     or
    1.45
     problems
    1.42
     especially
    1.42
     difficult
    1.34
     excessive
    1.30
     all
    1.30
     caused
    1.30
    Activations Density 0.044%

    No Known Activations