© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26799
    Prev
    Next
    INDEX
    Explanations

    program documentation

    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
     egenskaper
    -1.29
     constater
    -1.17
     arrêt
    -1.16
     miljö
    -1.16
     早餐
    -1.13
     kado
    -1.13
    czu
    -1.10
     yyj
    -1.09
     gorro
    -1.09
     verko
    -1.09
    POSITIVE LOGITS
     and
    1.28
     to
    1.22
     the
    1.18
    )
    1.05
     is
    1.05
     other
    1.01
     高校
    1.01
    ByUsername
    1.01
    );
    0.94
    ന്
    0.94
    Activations Density 0.001%

    No Known Activations