© 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. 25506
    Prev
    Next
    INDEX
    Explanations

    looking for True/IF conditions

    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
     Fleurit
    0.51
    不住
    0.47
     equivoc
    0.46
     Моло
    0.45
    忻
    0.45
    кратно
    0.45
     Treated
    0.45
    '`--'`--
    0.44
    ʡ
    0.44
    숴
    0.44
    POSITIVE LOGITS
     solicitud
    0.49
    in
    0.48
    ene
    0.48
    ants
    0.48
    development
    0.47
     i
    0.46
    er
    0.46
    ER
    0.46
    ules
    0.46
    ā
    0.46
    Activations Density 0.000%

    No Known Activations