© 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. 144731
    Prev
    Next
    INDEX
    Explanations

    aged, channel, relationship, actress

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

    media, religion, development

    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
    set
    0.66
    ser
    0.65
    ste
    0.61
    sets
    0.59
    sha
    0.59
    g
    0.59
    described
    0.57
    thi
    0.57
    vi
    0.55
    shall
    0.54
    POSITIVE LOGITS
    メディア
    0.52
    女優
    0.51
    婫
    0.48
     ресур
    0.47
    遊戲
    0.47
    コンテンツ
    0.47
    MEDIA
    0.47
     চ্যানেল
    0.47
    Golem
    0.47
    ﻁ
    0.47
    Activations Density 0.001%

    No Known Activations