© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70460
    Prev
    Next
    INDEX
    Explanations

    Italian prefixes or 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
    ”،
    -2.59
    just
    -2.47
    ますが
    -2.31
    jsonwebtoken
    -2.30
    Isso
    -2.23
     てる
    -2.20
    이크
    -2.20
    but
    -2.20
    این
    -2.19
     ngunit
    -2.19
    POSITIVE LOGITS
    {
    4.44
    ?"
    3.50
     This
    3.47
     Then
    2.58
    (
    2.47
     was
    2.41
     Historically
    2.38
     Würde
    2.33
     Due
    2.28
     solamente
    2.23
    Activations Density 0.003%

    No Known Activations