© 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. 22-GEMMASCOPE-RES-131K
    7. 27463
    Prev
    Next
    INDEX
    Explanations

    code snippets and configurations

    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
     Audiodateien
    -1.05
     पहले
    -1.05
    >",
    -1.02
     chè
    -1.02
     ſte
    -1.01
    eneral
    -0.99
     bemer
    -0.98
    ząt
    -0.98
     aprend
    -0.98
    __[
    -0.98
    POSITIVE LOGITS
     will
    1.17
     (
    1.16
     also
    1.11
     from
    1.07
     after
    1.05
     again
    1.05
    今度は
    1.00
     want
    0.98
     on
    0.98
     with
    0.96
    Activations Density 0.025%

    No Known Activations