© 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. 48486
    Prev
    Next
    INDEX
    Explanations

    case numbers and court documents

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

    The neuron strongly activates on numeric tokens and codes (e.g. version numbers, IDs, parameter values) in structured/config 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_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
    onnaissance
    -0.75
    ZERO
    -0.66
     reconnaissance
    -0.65
     penultimate
    -0.65
    HOUT
    -0.65
    firi
    -0.64
     penger
    -0.64
     Miri
    -0.62
    лерея
    -0.62
     ZERO
    -0.61
    POSITIVE LOGITS
    内外
    0.79
     dopas
    0.71
     Sci
    0.68
     packaging
    0.68
    dehydes
    0.68
    vemos
    0.67
    lind
    0.67
     Potomac
    0.66
    crust
    0.66
     öst
    0.65
    Activations Density 0.097%

    No Known Activations