© 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. 71398
    Prev
    Next
    INDEX
    Explanations

    prefix words

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

    The neuron is sensitive to metadata tokens—titles, section‐header words, dates, numbers, and other document‐structure markers.

    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
     krak
    -1.65
     kalender
    -1.63
     Uniwers
    -1.60
    〉
    -1.58
     kanker
    -1.56
     elektrische
    -1.55
     moft
    -1.55
     nowe
    -1.52
     rallado
    -1.51
     Hoje
    -1.50
    POSITIVE LOGITS
    Other
    1.76
    After
    1.56
    Here
    1.53
     or
    1.52
    During
    1.47
    There
    1.46
     also
    1.45
    Almost
    1.45
     всегда
    1.44
    However
    1.42
    Activations Density 0.245%

    No Known Activations