© 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. 160760
    Prev
    Next
    INDEX
    Explanations

    phrases with "or", "shall", "for"

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

    academic and technical terms

    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
    しい
    0.54
     מש
    0.52
     zegt
    0.51
     était
    0.50
     נק
    0.50
    噠
    0.50
     במ
    0.49
     ש
    0.49
     sabato
    0.49
     гром
    0.48
    POSITIVE LOGITS
    Other
    0.55
     Other
    0.54
    Draw
    0.52
    Sqrt
    0.51
    相邻
    0.48
    OH
    0.46
    LH
    0.45
    ෛ
    0.44
    taken
    0.44
    utives
    0.43
    Activations Density 0.000%

    No Known Activations