© 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. 184235
    Prev
    Next
    INDEX
    Explanations

    private conversation

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

    exploring complexities

    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
    弹
    0.47
    》，
    0.46
     SCHEDULE
    0.44
     MOBILE
    0.44
     appr
    0.44
     학생
    0.43
     modList
    0.43
     INVESTMENT
    0.42
    桠
    0.42
     endothelial
    0.42
    POSITIVE LOGITS
    inos
    0.46
     mayoral
    0.46
     जताया
    0.44
     died
    0.43
     নাক
    0.42
     mysteriously
    0.42
     may
    0.41
     é
    0.41
    ருக்கு
    0.41
     رائے
    0.41
    Activations Density 0.001%

    No Known Activations