© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6980
    Prev
    Next
    INDEX
    Explanations

    bullet points

    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
     in
    -0.99
     on
    -0.95
     neu
    -0.81
    menor
    -0.81
     centro
    -0.81
    getPackageName
    -0.79
     solitario
    -0.79
     Matt
    -0.78
     bereits
    -0.77
     aventuras
    -0.77
    POSITIVE LOGITS
    *
    3.28
     *
    2.20
    *
    
    1.87
    *",
    1.66
    *;
    1.65
    *,
    1.63
    *:
    1.51
    *),
    1.48
    *.
    1.47
    *}
    1.45
    Activations Density 0.027%

    No Known Activations