© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12064
    Prev
    Next
    INDEX
    Explanations

    data scanning or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ి
    0.66
     olisi
    0.65
    型的
    0.63
     बंधन
    0.63
     بودم
    0.63
    gning
    0.62
     গান্ধ
    0.61
    मध
    0.61
     האט
    0.61
     did
    0.61
    POSITIVE LOGITS
    c
    0.95
    いつでも
    0.87
     Nightmare
    0.80
     Eliza
    0.80
     Rocha
    0.79
    もちろん
    0.79
     Burden
    0.78
     lượt
    0.77
     Stella
    0.76
     Anglican
    0.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.