© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201119
    Prev
    Next
    INDEX
    Explanations

    reduce, reuse, recycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    0.49
    idam
    0.44
     LIB
    0.43
    combine
    0.42
    ⌈
    0.41
     trava
    0.40
     <
    0.40
     thermodynamics
    0.39
    t
    0.39
    ^{-
    0.39
    POSITIVE LOGITS
     diaries
    0.55
    ificaciones
    0.53
     कोरिया
    0.53
    کی
    0.51
    igneur
    0.50
    йної
    0.46
     tattooed
    0.45
     celebrities
    0.45
    izie
    0.44
    িয়ে
    0.44
    Activations Density 0.002%

    No Known Activations