© 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. 34-GEMMASCOPE-RES-131K
    7. 73376
    Prev
    Next
    INDEX
    Explanations

    models related_name or collection_name

    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_34/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
    setValue
    -0.87
    *<
    -0.81
    /**
    -0.81
    لة
    -0.80
    getValue
    -0.78
    neau
    -0.77
    τους
    -0.77
    ilsen
    -0.77
     sonunda
    -0.77
    }));
    -0.76
    POSITIVE LOGITS
     related
    1.32
     on
    1.20
    Related
    1.09
     Related
    1.04
     RELATED
    0.98
     limiting
    0.89
    related
    0.89
     ON
    0.86
     limit
    0.84
    limit
    0.81
    Activations Density 0.003%

    No Known Activations