© 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. 10-GEMMASCOPE-RES-131K
    7. 85152
    Prev
    Next
    INDEX
    Explanations

    Adolph, Rudolph, Randolph, Julius names

    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
     "
    -3.41
    '
    -2.94
    =
    -2.89
     '
    -2.86
     -
    -2.61
    ...
    -2.58
    end
    -2.53
     is
    -2.48
    t
    -2.42
    -"
    -2.34
    POSITIVE LOGITS
    噐
    2.84
    ité
    2.67
    ,’
    2.53
     笔画
    2.52
    輋
    2.50
    ión
    2.44
    也
    2.42
    婞
    2.42
     brancas
    2.42
    ientras
    2.42
    Activations Density 0.016%

    No Known Activations