© 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. 109715
    Prev
    Next
    INDEX
    Explanations

    approximations and states

    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
    কাতে
    0.45
    ཊ
    0.44
    खास्त
    0.42
    ScreenBinding
    0.42
    Ⲑ
    0.42
    ༌
    0.42
     इत्यादि
    0.41
    サーチ
    0.40
    ਠ
    0.40
    を通じて
    0.40
    POSITIVE LOGITS
     Sal
    0.49
     Lim
    0.45
     Plus
    0.45
     Dist
    0.44
     Relationships
    0.44
     Review
    0.43
     prote
    0.42
     How
    0.42
     Ade
    0.42
     Yard
    0.41
    Activations Density 0.000%

    No Known Activations