© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12480
    Prev
    Next
    INDEX
    Explanations

    punctuation and unrelated tokens

    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
    ());//
    -1.01
    採
    -0.86
    Formulation
    -0.86
    Suggestions
    -0.85
     labi
    -0.83
    Spice
    -0.83
     spil
    -0.83
    溜
    -0.83
     desu
    -0.82
    只见
    -0.82
    POSITIVE LOGITS
    *}
    0.96
    áját
    0.96
     Darstellung
    0.95
    ఉ
    0.94
     Werken
    0.93
    ным
    0.91
    xas
    0.91
     sukienka
    0.90
     tillegg
    0.90
    ently
    0.89
    Activations Density 0.004%

    No Known Activations