© 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. 28319
    Prev
    Next
    INDEX
    Explanations

    game, power, AI, egg

    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
    Tarjeta
    0.51
    擔任
    0.45
     መካከል
    0.44
    ية
    0.44
    Tar
    0.43
    *}$
    0.43
    좔
    0.43
    <unused213>
    0.42
    人员
    0.41
     Tar
    0.41
    POSITIVE LOGITS
     activates
    0.49
     utilises
    0.45
     implementations
    0.44
     PLUS
    0.44
     ACTIV
    0.43
     Utilize
    0.43
     regions
    0.43
     Utilization
    0.42
     DER
    0.42
     Thailand
    0.42
    Activations Density 0.004%

    No Known Activations