© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74611
    Prev
    Next
    INDEX
    Explanations

    understanding or misunderstanding concepts

    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
     then
    -1.45
    chaqueta
    -1.37
     ͡
    -1.31
    
    -1.31
    ts
    -1.30
    を経て
    -1.30
    tigheter
    -1.28
     vegeta
    -1.25
    งิน
    -1.23
     们
    -1.23
    POSITIVE LOGITS
    enerbah
    1.38
     and
    1.28
     OGSÅ
    1.20
    usap
    1.19
     "...
    1.17
    ündigung
    1.16
    Gilla
    1.15
     new
    1.14
    那些
    1.13
    mphs
    1.13
    Activations Density 0.090%

    No Known Activations