© 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. 40102
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by "model"

    np_acts-logits-general · gemini-2.5-flash-lite

    `l` or `L`

    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
    larını
    0.99
    ی
    0.96
    y
    0.91
    ları
    0.88
    лари
    0.86
    ைகள்
    0.86
    et
    0.85
    arah
    0.85
    ک
    0.82
    さ
    0.82
    POSITIVE LOGITS
    l
    1.20
    ل
    1.02
    icious
    0.91
    anguage
    0.89
    은
    0.89
    ر
    0.85
    ibrary
    0.84
    л
    0.81
    the
    0.79
    ל
    0.78
    Activations Density 0.213%

    No Known Activations