© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248179
    Prev
    Next
    INDEX
    Explanations

    starting punctuation, separators, and conjunctions

    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
    స్త్ర
    0.47
    ĝ
    0.45
    蛯
    0.44
    endre
    0.44
    ිට
    0.44
    有用
    0.42
    େ
    0.42
    год
    0.42
    此
    0.42
    桷
    0.42
    POSITIVE LOGITS
     FROM
    0.44
     mesmerizing
    0.41
     ethereal
    0.41
    Hundreds
    0.41
    ('['
    0.40
    แหล่ง
    0.40
     dazz
    0.40
    ("["
    0.39
    ンドン
    0.39
     kaleidoscopic
    0.39
    Activations Density 0.000%

    No Known Activations