© 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. 34606
    Prev
    Next
    INDEX
    Explanations

    lookup, kpi, todo, new, rotten, external, access, update

    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
    zmm
    -1.16
     tradicionais
    -1.08
    ğın
    -1.05
    alberto
    -1.05
     bekom
    -1.05
    嫫
    -1.05
    krish
    -1.04
    ゲット
    -1.01
    infect
    -1.01
    makta
    -1.00
    POSITIVE LOGITS
     sogar
    1.15
    tismo
    1.08
    ulation
    1.01
    ◈
    0.99
    พ์
    0.99
     ''
    0.97
    P
    0.97
    Adverten
    0.96
     '',
    0.96
    全ての
    0.96
    Activations Density 0.018%

    No Known Activations