© 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. 131568
    Prev
    Next
    INDEX
    Explanations

    specialist to book

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

    skip, than, never

    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
     因為
    0.65
     書い
    0.59
     ትንሽ
    0.58
     พวก
    0.57
     व
    0.57
     เพิ่ม
    0.56
    ర
    0.56
     而且
    0.55
     他们
    0.55
     eigenen
    0.55
    POSITIVE LOGITS
    jetbrains
    0.47
    not
    0.46
    kh
    0.45
    nie
    0.45
    Nik
    0.44
    ni
    0.43
    clear
    0.43
    ходи
    0.42
    )
    0.42
    ruar
    0.41
    Activations Density 0.000%

    No Known Activations