© 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. 9510
    Prev
    Next
    INDEX
    Explanations

    discussions about studies claims

    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
    MAXN
    -1.44
    ilyen
    -1.37
    كون
    -1.30
     lesquels
    -1.21
     lesquelles
    -1.20
    あなたの
    -1.20
     you
    -1.19
     CHALLENGE
    -1.16
     ",";
    -1.16
    この
    -1.15
    POSITIVE LOGITS
     on
    1.73
     to
    1.53
     also
    1.44
     in
    1.36
     about
    1.27
     incluso
    1.27
     everything
    1.20
     around
    1.17
    大な
    1.16
     along
    1.14
    Activations Density 0.170%

    No Known Activations