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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11593
    Prev
    Next
    INDEX
    Explanations

    research and applied findings

    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
    ?』
    -1.26
    ⚢
    -1.21
     воспользоваться
    -1.21
     fermer
    -1.19
    axaca
    -1.19
     MATER
    -1.18
     directement
    -1.18
    וקה
    -1.17
    があるので
    -1.16
    𓍊
    -1.16
    POSITIVE LOGITS
     of
    1.36
     There
    1.24
     the
    1.20
     new
    1.19
     The
    1.14
    '
    1.12
     ofreci
    1.11
     H
    1.09
     You
    1.09
     are
    1.08
    Activations Density 0.006%

    No Known Activations