© 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. 10-GEMMASCOPE-RES-131K
    4. 21
    Prev
    Next
    INDEX
    Explanations

    stars, exoplanets, light curve variability

    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
    $
    -1.30
    ang
    -1.27
    os
    -1.24
    ных
    -1.21
    ti
    -1.16
    end
    -1.16
    in
    -1.16
    et
    -1.14
    us
    -1.14
    on
    -1.13
    POSITIVE LOGITS
     also
    1.45
     myös
    1.30
     également
    1.25
     también
    1.18
    lepší
    1.17
    CWE
    1.17
     أيضا
    1.16
    luß
    1.15
     estimular
    1.13
    //-->
    1.10
    Activations Density 0.041%

    No Known Activations