© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84924
    Prev
    Next
    INDEX
    Explanations

    Transfer to, spending the, long story

    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
     другую
    -1.52
    ↵
    -1.34
     interessa
    -1.21
    がありました
    -1.15
    >");
    -1.15
     каждого
    -1.14
     gefe
    -1.14
     "];
    -1.14
    cursions
    -1.14
     diversos
    -1.13
    POSITIVE LOGITS
     or
    1.40
     with
    1.35
     on
    1.28
     soothing
    1.22
     насеље
    1.18
     uber
    1.15
    hý
    1.15
     your
    1.14
     chilling
    1.13
    чис
    1.13
    Activations Density 0.014%

    No Known Activations