© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11467
    Prev
    Next
    INDEX
    Explanations

    titles, abbreviations, or beginnings

    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_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
     you
    -1.38
     {
    -1.20
    lossians
    -1.16
     their
    -1.13
    lepiej
    -1.12
     of
    -1.09
     or
    -1.09
    ocardial
    -1.08
    者が
    -1.04
    ())));
    -1.04
    POSITIVE LOGITS
    がありますが
    1.57
     réessayer
    1.30
    oping
    1.28
    鉭
    1.28
     クーポン
    1.25
    appears
    1.18
    かげ
    1.17
     distinto
    1.17
     certaines
    1.14
    Opciones
    1.13
    Activations Density 0.000%

    No Known Activations