Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7606
    Prev
    Next
    INDEX
    Explanations

    words starting with wig, wick, bick, brig, vig, wik, fig

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     screamed
    -0.81
    ័
    -0.77
    buatan
    -0.77
    sikker
    -0.75
    dshaw
    -0.72
    ဵ
    -0.72
    %\]
    -0.72
     PHOTO
    -0.71
     screams
    -0.71
    angkutan
    -0.70
    POSITIVE LOGITS
    nell
    0.91
    NELL
    0.82
     vig
    0.76
    AccessException
    0.75
    ots
    0.75
     arru
    0.73
    ining
    0.73
    ingly
    0.73
    yled
    0.72
     Vict
    0.70
    Activations Density 0.030%

    No Known Activations