© 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. 40-GEMMASCOPE-2-RES-262K
    7. 109597
    Prev
    Next
    INDEX
    Explanations

    intentionally kept/keeping

    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_40_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
    рина
    0.40
    चार्य
    0.39
    ండ
    0.39
     Gecko
    0.39
    مانی
    0.38
     barge
    0.37
    в
    0.37
     بیک
    0.37
    روی
    0.36
     decomposed
    0.36
    POSITIVE LOGITS
    боре
    0.41
     '\\;'
    0.40
    iação
    0.38
    界的
    0.38
    LER
    0.37
    itm
    0.37
     δύ
    0.37
    ඩා
    0.37
     utf
    0.36
     ″
    0.36
    Activations Density 0.000%

    No Known Activations