© 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. 9565
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
     других
    -0.92
    gimento
    -0.88
    惊讶
    -0.88
     clásica
    -0.88
     both
    -0.84
     voks
    -0.82
     Turm
    -0.82
     Recently
    -0.82
     masculina
    -0.81
     føl
    -0.81
    POSITIVE LOGITS
     Vai
    0.92
    ensacola
    0.88
    }],
    0.85
     HOU
    0.82
     his
    0.82
    teli
    0.80
    ונה
    0.79
     coste
    0.79
     consigli
    0.79
     realmente
    0.79
    Activations Density 0.019%

    No Known Activations