© 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. 10-GEMMASCOPE-RES-131K
    7. 100187
    Prev
    Next
    INDEX
    Explanations

    one of the most significant

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

    The neuron flags numeric tokens (quantities and measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    in
    -1.98
    la
    -1.72
     on
    -1.56
    x
    -1.51
    inverno
    -1.50
    D
    -1.44
    lo
    -1.37
    j
    -1.36
    on
    -1.35
    li
    -1.34
    POSITIVE LOGITS
     that
    1.98
     idén
    1.67
     podéis
    1.58
     nécessite
    1.56
     reason
    1.55
    ühnen
    1.53
    釹
    1.51
    蒾
    1.50
    苼
    1.50
    mband
    1.48
    Activations Density 0.024%

    No Known Activations