© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57594
    Prev
    Next
    INDEX
    Explanations

    Angus Cottage, Superfly, Tacuba

    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_10/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
     啦
    -1.20
     Cuen
    -1.12
     fluff
    -1.10
     možnost
    -1.05
    In
    -1.05
    WORLD
    -1.05
     особенно
    -1.04
     naš
    -1.04
    RoleName
    -1.02
    /$',
    -1.01
    POSITIVE LOGITS
    的
    1.38
     cantit
    1.30
    adă
    1.30
    тур
    1.29
    other
    1.25
     others
    1.25
     titolo
    1.24
    </b>
    1.24
    esthes
    1.20
     sposa
    1.20
    Activations Density 0.434%

    No Known Activations