© 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. 40244
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions followed by common nouns

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

    parameters and sizes

    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
     수학
    0.46
    훑
    0.45
    প্তাহ
    0.42
     می‌شود
    0.42
    会将
    0.42
    베이스
    0.41
    및
    0.41
    朗普
    0.40
    දේශ
    0.40
    녠
    0.40
    POSITIVE LOGITS
     exorbit
    0.56
     aumentado
    0.50
     euphoria
    0.49
     despair
    0.49
     potre
    0.49
     потенциа
    0.47
    .\
    0.46
     Toma
    0.46
     drows
    0.46
    __);
    0.45
    Activations Density 0.000%

    No Known Activations