© 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. 22-GEMMASCOPE-RES-131K
    4. 66157
    Prev
    Next
    INDEX
    Explanations

    api response data handling

    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_22/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
     to
    -1.41
     with
    -1.32
     A
    -1.27
     at
    -1.23
     for
    -1.20
     By
    -1.18
     under
    -1.13
     To
    -1.04
     At
    -1.02
     M
    -1.00
    POSITIVE LOGITS
    킁
    1.42
     reager
    1.28
    臯
    1.23
     tortuga
    1.22
     PLATES
    1.22
     NEGRO
    1.20
    不一样的
    1.19
    És
    1.17
     diamante
    1.17
    Один
    1.16
    Activations Density 0.003%

    No Known Activations