© 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. 145813
    Prev
    Next
    INDEX
    Explanations

    website updates and details

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

    biomass, insurance, physics, coding, space

    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
    Instructor
    0.53
    Seventh
    0.49
    AN
    0.48
     Clauses
    0.47
    HALF
    0.47
    RAFT
    0.46
    —
    0.45
    \"
    0.44
    Optional
    0.44
    An
    0.43
    POSITIVE LOGITS
     embroidery
    0.54
     Kimball
    0.53
     defocus
    0.52
     मलयालम
    0.50
     ഓൺലൈ
    0.48
    刺繍
    0.47
    akili
    0.47
    ronic
    0.47
     অনলাইন
    0.47
     कोशिकाओं
    0.47
    Activations Density 0.000%

    No Known Activations