© 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. 96285
    Prev
    Next
    INDEX
    Explanations

    foreign languages and media

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

    parenthetical stage directions or actions

    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
     apical
    0.46
    ophylline
    0.40
    👦
    0.39
    iculo
    0.38
    IDOS
    0.38
     отече
    0.38
     sacram
    0.37
     Carolina
    0.36
     labile
    0.35
     aspirated
    0.35
    POSITIVE LOGITS
     مات
    0.47
     अनियमित
    0.45
    攀
    0.42
    传说
    0.42
    缰
    0.42
    الف
    0.42
     فيديو
    0.41
     ड्रोन
    0.40
    微信
    0.40
     playlist
    0.39
    Activations Density 0.015%

    No Known Activations