© 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. 153386
    Prev
    Next
    INDEX
    Explanations

    prepositions following certain verbs/nouns

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

    content moderation or refusal

    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
    ส
    0.65
    و
    0.47
    Community
    0.42
    до
    0.42
    money
    0.42
    community
    0.42
    স
    0.41
    ร
    0.40
    financial
    0.40
    Storage
    0.40
    POSITIVE LOGITS
    .°
    0.51
     Ell
    0.50
    बीन
    0.50
     όπως
    0.50
     UIS
    0.48
     Congrès
    0.47
     Warfare
    0.47
     UNESCO
    0.47
     Raffa
    0.46
     Το
    0.46
    Activations Density 0.000%

    No Known Activations