© 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. 71177
    Prev
    Next
    INDEX
    Explanations

    en route to

    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
    衕
    -2.17
    หรือ
    -2.17
    
    -2.06
     encontrados
    -2.05
     beziehungs
    -2.03
    瓩
    -1.97
    𔘓
    -1.95
    ).
    -1.95
    );
    -1.95
    ができます
    -1.91
    POSITIVE LOGITS
     Inſ
    2.50
    eterangan
    2.11
     Not
    1.99
     But
    1.95
     Perſ
    1.92
     Reſ
    1.91
     Houſe
    1.88
    "
    1.85
     were
    1.84
     They
    1.81
    Activations Density 0.002%

    No Known Activations