© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169868
    Prev
    Next
    INDEX
    Explanations

    deviating from traditional sense

    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
    는
    0.48
    ింది
    0.46
    HttpClient
    0.46
    Omega
    0.46
    K
    0.44
    H
    0.44
     Phang
    0.43
    P
    0.43
    Sparse
    0.43
    Gam
    0.42
    POSITIVE LOGITS
     menu
    0.49
     goede
    0.48
     minimum
    0.46
     penis
    0.46
     measurement
    0.45
     risen
    0.45
     for
    0.44
     onus
    0.44
     measure
    0.44
    mls
    0.43
    Activations Density 0.003%

    No Known Activations