© 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. 161211
    Prev
    Next
    INDEX
    Explanations

    clogged pores, slightly modified, select stores

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

    gaze, knowing eyes, specific remarks

    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
    ت
    0.54
     of
    0.53
    ედერ
    0.48
    リュー
    0.47
    Т
    0.47
     Rü
    0.47
    োগ্র
    0.46
    د
    0.46
     NumPy
    0.46
    Са
    0.46
    POSITIVE LOGITS
    ate
    0.54
    nect
    0.49
    atore
    0.48
    ếc
    0.47
    neck
    0.47
    iatric
    0.46
    slow
    0.44
    stone
    0.42
    ano
    0.42
    weeney
    0.42
    Activations Density 0.000%

    No Known Activations