© 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. 128841
    Prev
    Next
    INDEX
    Explanations

    resources, protector, discover, language, across, designing

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

    calculating layers

    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
    ரி
    0.50
     Terri
    0.49
     inte
    0.49
     interests
    0.49
    Inte
    0.48
    #!/
    0.46
     interess
    0.46
    😈
    0.46
    📊
    0.46
     obedience
    0.44
    POSITIVE LOGITS
    p
    0.55
    pose
    0.54
    m
    0.54
    catch
    0.52
    t
    0.52
    texture
    0.52
    pre
    0.51
    turn
    0.50
    birthday
    0.50
    violet
    0.49
    Activations Density 0.000%

    No Known Activations