© 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. 43671
    Prev
    Next
    INDEX
    Explanations

    Lord, mode, pass, aw

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

    kill off

    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
    كي
    0.59
    בק
    0.58
    秪
    0.57
    م
    0.55
    מה
    0.52
     restraining
    0.52
    ಹೆ
    0.52
    لما
    0.52
    كان
    0.51
    كل
    0.50
    POSITIVE LOGITS
    </h1>
    0.50
     are
    0.48
     bits
    0.44
    slip
    0.44
     flute
    0.44
    =
    0.44
     handy
    0.43
     අනුව
    0.43
     video
    0.42
    church
    0.42
    Activations Density 0.000%

    No Known Activations