© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 17957
    Prev
    Next
    INDEX
    Explanations

    auto, max, new, numeric, english

    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
     Default
    0.52
     NULL
    0.44
    Default
    0.43
     Editable
    0.41
     Typical
    0.39
    দের
    0.38
     bypassing
    0.38
    6
    0.37
    χα
    0.37
    üm
    0.36
    POSITIVE LOGITS
     darb
    0.47
     ട്ര
    0.39
     علينا
    0.38
    Sri
    0.38
    Kami
    0.37
     Erick
    0.37
     Monterrey
    0.35
    氳
    0.35
    件事
    0.35
    -}$
    0.35
    Activations Density 0.010%

    No Known Activations