© 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. 10-GEMMASCOPE-RES-131K
    4. 128717
    Prev
    Next
    INDEX
    Explanations

    Japanese titles, ship names, introductions

    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_10/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
    或者
    -3.44
    to
    -3.28
     یا
    -2.92
     eller
    -2.77
    或
    -2.63
     atau
    -2.48
     dizzy
    -2.34
     или
    -2.31
     oder
    -2.30
    ↵↵
    -2.28
    POSITIVE LOGITS
    ,"
    2.73
     "
    2.63
    ),
    2.42
     Specially
    2.41
    The
    2.41
    ).
    2.39
    ."
    2.38
     This
    2.34
    ariously
    2.33
    甃
    2.25
    Activations Density 0.000%

    No Known Activations