© 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. 34-GEMMASCOPE-RES-131K
    7. 63116
    Prev
    Next
    INDEX
    Explanations

    describing a characteristic or type

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

    The neuron activates on numeric tokens (e.g. integers) in scientific passages, highlighting measurements or counts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    SharedModule
    -1.11
    ïc
    -1.04
     tots
    -0.99
    漲
    -0.93
     sora
    -0.92
    Notae
    -0.91
    env
    -0.91
    sz
    -0.90
     tric
    -0.90
    ٥
    -0.90
    POSITIVE LOGITS
     many
    1.48
     modern
    1.47
     any
    1.42
     complex
    1.41
     a
    1.40
     large
    1.32
     ANY
    1.22
     highly
    1.18
     such
    1.16
     both
    1.15
    Activations Density 0.557%

    No Known Activations