© 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. 72340
    Prev
    Next
    INDEX
    Explanations

    RSVP requested

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

    even like some for

    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
    ita
    0.55
    Isl
    0.52
    Ofer
    0.51
    úa
    0.50
    uene
    0.50
    тері
    0.50
    utia
    0.49
    信
    0.48
    atorics
    0.48
    ponent
    0.47
    POSITIVE LOGITS
     bumped
    0.43
     Reservations
    0.43
    ành
    0.43
     شک
    0.43
     gây
    0.43
     CCN
    0.42
     bookings
    0.42
     réunion
    0.41
     Conversations
    0.41
     Vocês
    0.41
    Activations Density 0.000%

    No Known Activations