© 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. 191708
    Prev
    Next
    INDEX
    Explanations

    numbers and scores

    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
     whirl
    0.46
     ಅಲ
    0.43
     knives
    0.41
    experts
    0.40
    ืด
    0.39
     lightening
    0.39
    horsepower
    0.39
     ғ
    0.38
    रिक
    0.38
    realistic
    0.38
    POSITIVE LOGITS
    VD
    0.39
     thêm
    0.37
     Toc
    0.36
     VD
    0.35
    椪
    0.35
    نما
    0.35
     Table
    0.35
     -->
    0.35
     EC
    0.35
     iban
    0.35
    Activations Density 0.003%

    No Known Activations