© 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. 211519
    Prev
    Next
    INDEX
    Explanations

    whimsical, Studying, Cat, recognize, likely

    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
    isting
    0.45
    Fat
    0.44
    nhs
    0.43
    Disabled
    0.42
    Contributing
    0.42
    ifiziert
    0.42
    ="#"
    0.42
    Halo
    0.41
    فاق
    0.41
    Wright
    0.40
    POSITIVE LOGITS
     distribute
    0.40
    ⵜ
    0.40
     variations
    0.39
     distributional
    0.39
     onshore
    0.38
     distribut
    0.38
    asilkan
    0.38
     begin
    0.36
     regi
    0.36
     mainland
    0.36
    Activations Density 0.001%

    No Known Activations