© 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. 35109
    Prev
    Next
    INDEX
    Explanations

    website offers

    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
     two
    -1.15
     three
    -1.08
     mecan
    -1.05
    ජ
    -1.00
     vei
    -0.96
     miraculous
    -0.96
     Aner
    -0.96
    ありません
    -0.96
    êmica
    -0.94
     innumerable
    -0.94
    POSITIVE LOGITS
     here
    1.25
     also
    1.16
     dettagli
    1.05
    alians
    1.04
    coden
    1.02
    トイ
    0.99
     website
    0.96
     https
    0.95
    Estos
    0.95
    に興味
    0.94
    Activations Density 0.003%

    No Known Activations