© 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. 46611
    Prev
    Next
    INDEX
    Explanations

    book appointments

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

    desire, practice, containers, texts, bugs, values, acceptable, intent

    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
    Điều
    0.55
    લાઇ
    0.54
    ло
    0.51
     điều
    0.51
    ли
    0.51
    使用
    0.50
    ത
    0.50
    調
    0.50
    де
    0.49
    美しい
    0.49
    POSITIVE LOGITS
     totalitarian
    0.50
     sprawl
    0.49
    —
    0.46
     lawn
    0.46
     rosette
    0.46
     penthouse
    0.45
     mañana
    0.45
     giusto
    0.45
     punk
    0.45
     hernia
    0.45
    Activations Density 0.000%

    No Known Activations