© 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. 27436
    Prev
    Next
    INDEX
    Explanations

    no one

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

    absence of features

    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
    r
    0.96
    ي
    0.82
    ви
    0.82
    y
    0.81
    i
    0.81
    u
    0.81
    w
    0.80
    ut
    0.79
    <h4>
    0.77
    ě
    0.77
    POSITIVE LOGITS
    ۱
    0.89
    ۲
    0.82
    치
    0.81
    거나
    0.80
    1
    0.80
    舩
    0.80
    ভাবেই
    0.78
    ль
    0.76
     لی
    0.75
    最後に
    0.75
    Activations Density 0.099%

    No Known Activations