© 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. 60159
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions followed by nouns

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

    role-playing conversational phrases

    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
    on
    0.67
    i
    0.52
    an
    0.49
    emap
    0.48
    LocalStorage
    0.46
     Fuse
    0.46
    A
    0.46
    u
    0.46
    ে
    0.45
    フィス
    0.45
    POSITIVE LOGITS
     constantemente
    0.64
     tradición
    0.54
     posición
    0.54
     rápidamente
    0.53
     cancelación
    0.52
     escuch
    0.50
     değer
    0.50
     своих
    0.50
     Ünivers
    0.49
     köpek
    0.49
    Activations Density 0.000%

    No Known Activations