© 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. 27882
    Prev
    Next
    INDEX
    Explanations

    structs and enums

    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
    皤
    -1.63
    蟶
    -1.53
     Posteriormente
    -1.53
     dépenses
    -1.48
    WHY
    -1.45
     Asimismo
    -1.43
    También
    -1.42
    蛱
    -1.41
     zrobić
    -1.41
     lorsque
    -1.39
    POSITIVE LOGITS
     not
    1.66
     which
    1.60
     that
    1.55
     achieving
    1.51
     but
    1.45
    1.45
     at
    1.41
     including
    1.40
     fleste
    1.39
     all
    1.38
    Activations Density 0.021%
    No Known Activations