© 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. 25338
    Prev
    Next
    INDEX
    Explanations

    technical terms and their purpose

    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
     this
    -1.67
    瞜
    -1.48
    ＊＊＊＊
    -1.39
    にほんブログ村
    -1.38
     écoute
    -1.38
     тоже
    -1.36
     CONCEP
    -1.35
    久し
    -1.35
     Ibidem
    -1.35
     productie
    -1.30
    POSITIVE LOGITS
    が
    1.54
     to
    1.27
    では
    1.26
    で
    1.26
     He
    1.23
    を
    1.20
     who
    1.20
    ípio
    1.19
    は
    1.16
     is
    1.14
    Activations Density 0.043%

    No Known Activations