© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228905
    Prev
    Next
    INDEX
    Explanations

    built in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    敘
    0.46
    Population
    0.45
    وو
    0.44
    ترة
    0.43
    ストア
    0.43
    We
    0.43
    กระจ
    0.43
    '
    0.43
    ジョン
    0.43
    Election
    0.42
    POSITIVE LOGITS
    𝒍
    0.53
    ंगत
    0.49
    नाटक
    0.49
    getTotal
    0.48
    leriyle
    0.48
    ılan
    0.48
     paheli
    0.48
    łego
    0.47
    ोटी
    0.47
     throat
    0.47
    Activations Density 0.000%

    No Known Activations