© 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. 16233
    Prev
    Next
    INDEX
    Explanations

    this or your

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

    explains why

    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
     ત્રણ
    0.45
    4
    0.42
    7
    0.40
    6
    0.38
    5
    0.37
     επίσης
    0.37
     vendidos
    0.37
    3
    0.36
     עם
    0.36
    getRedTeam
    0.36
    POSITIVE LOGITS
     этой
    0.69
     dieser
    0.66
     цього
    0.66
     this
    0.65
     tohoto
    0.65
     tejto
    0.65
     acest
    0.63
     této
    0.62
     этого
    0.61
     این
    0.61
    Activations Density 0.168%

    No Known Activations