© 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. 89562
    Prev
    Next
    INDEX
    Explanations

    island names

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

    cocktail or Rosé

    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
    pt
    0.54
    be
    0.53
    pin
    0.52
    pref
    0.49
    mi
    0.48
    ち
    0.47
    ani
    0.47
    ping
    0.47
    esthetic
    0.47
    stro
    0.46
    POSITIVE LOGITS
     Haji
    0.55
     Sereth
    0.50
     Airt
    0.49
    넉
    0.49
    ී
    0.49
    Abdul
    0.48
     Airl
    0.48
     Trabal
    0.48
    AuditEvent
    0.47
     Expenses
    0.47
    Activations Density 0.000%

    No Known Activations