© 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. 34-GEMMASCOPE-RES-131K
    7. 3004
    Prev
    Next
    INDEX
    Explanations

    academic paper metadata

    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_34/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
    notNull
    -0.95
     cũng
    -0.84
     tami
    -0.80
    entas
    -0.80
    鐢
    -0.79
    WEBP
    -0.78
     labd
    -0.75
    ٘
    -0.75
    Finally
    -0.74
     罗
    -0.74
    POSITIVE LOGITS
     {
    1.44
     {},
    1.30
    ัท
    1.06
    diğ
    0.90
     {};
    0.88
     manteiga
    0.83
    }';
    0.80
    覗
    0.79
    cetti
    0.77
     कोश
    0.77
    Activations Density 0.027%

    No Known Activations