© 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. 22358
    Prev
    Next
    INDEX
    Explanations

    closing of | major regulatory | bit ring | child at

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

    common words introducing specifics

    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
    ’
    0.51
     Rott
    0.50
     authent
    0.48
     V
    0.47
    সভ
    0.46
     safely
    0.46
     Y
    0.46
     Ша
    0.46
    シャ
    0.46
     ponte
    0.46
    POSITIVE LOGITS
    エース
    0.49
    lobin
    0.47
     तळ
    0.47
    allenges
    0.46
    드를
    0.45
    wires
    0.45
    퇸
    0.45
    rimos
    0.45
     dày
    0.45
    acoes
    0.44
    Activations Density 0.000%

    No Known Activations