© 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. 44027
    Prev
    Next
    INDEX
    Explanations

    mentions or tags

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

    levels of or relateds

    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
    Жен
    0.49
    強制
    0.49
    大手
    0.47
    雄
    0.46
     hated
    0.45
    サイズの
    0.44
    砸
    0.44
    胸
    0.44
    IMPORT
    0.43
    感染
    0.42
    POSITIVE LOGITS
     angles
    0.50
    presentation
    0.47
    nál
    0.46
    ామ
    0.45
    devices
    0.44
    enable
    0.44
    ax
    0.43
     at
    0.43
     presentation
    0.43
     అవి
    0.42
    Activations Density 0.000%

    No Known Activations