© 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. 178733
    Prev
    Next
    INDEX
    Explanations

    requests for interviews and Kindle

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

    about characters|today|cost|no|gold|sorry|motivation

    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
     coarsely
    0.56
     authorized
    0.50
     linearized
    0.50
     entitled
    0.48
     colonized
    0.46
     constructively
    0.46
     linearly
    0.46
    ↵
    0.46
     maliciously
    0.46
     crystallized
    0.46
    POSITIVE LOGITS
     Semua
    0.52
    e
    0.52
    oo
    0.49
    விக்க
    0.49
     فرص
    0.47
     लक्षात
    0.47
     همه
    0.46
     mengapa
    0.46
    eyi
    0.45
     तुम्ही
    0.45
    Activations Density 0.001%

    No Known Activations