© 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. 64919
    Prev
    Next
    INDEX
    Explanations

    URLs and identifiers

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

    This neuron detects URL fragment‐identifier tokens—i.e. the “#.‹random-alphanumeric›” anchors (hash+dot+ID) used in links.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -1.04
     onCreateView
    -0.95
     again
    -0.93
    authService
    -0.90
     Menschen
    -0.90
     htmlFor
    -0.90
    هذا
    -0.88
     skry
    -0.88
     calldata
    -0.86
    šana
    -0.85
    POSITIVE LOGITS
    婀
    0.93
    不愿意
    0.92
    攔
    0.92
    schirm
    0.90
    つづく
    0.90
     начинают
    0.89
     ähn
    0.87
     peered
    0.86
    总会
    0.85
    我们将
    0.85
    Activations Density 0.001%

    No Known Activations