© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60557
    Prev
    Next
    INDEX
    Explanations

    names ending in ak

    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
     But
    -2.44
    真的很
    -2.33
     That
    -2.33
    楼梯
    -2.31
    鹉
    -2.20
    逦
    -2.17
     challenging
    -2.17
    ة
    -2.16
    ㄧ
    -2.16
    ות
    -2.13
    POSITIVE LOGITS
    ak
    4.06
    s
    3.88
    am
    3.53
    ay
    3.19
    ot
    3.13
    c
    2.98
    om
    2.97
    “
    2.92
    da
    2.92
    up
    2.92
    Activations Density 0.009%

    No Known Activations