© 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. 141482
    Prev
    Next
    INDEX
    Explanations

    web / console / bay

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

    descriptive starters or common connectors

    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
    यदि
    0.46
    आर
    0.45
    daily
    0.45
     departamentos
    0.45
     सर्वोच्च
    0.45
    cómo
    0.45
     proizvođa
    0.45
    ච
    0.45
     Nullam
    0.45
    ྒྱ
    0.45
    POSITIVE LOGITS
    مند
    0.45
    ุม
    0.44
    ilized
    0.43
    antiates
    0.43
    Lm
    0.42
    LIK
    0.42
     whis
    0.41
    Mouse
    0.41
    لیفون
    0.41
    ämm
    0.40
    Activations Density 0.000%

    No Known Activations