© 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. 211638
    Prev
    Next
    INDEX
    Explanations

    dark eyes

    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
     अट
    0.40
    暌
    0.39
    𝓃
    0.39
     lè
    0.38
    烹
    0.37
    nur
    0.36
    Constitution
    0.36
     životu
    0.36
    മെ
    0.36
     चौपट
    0.36
    POSITIVE LOGITS
    륭
    0.45
     transitory
    0.42
     contributions
    0.41
     Contributions
    0.39
     Response
    0.39
     theoretical
    0.39
     kink
    0.38
     seasonal
    0.38
     response
    0.38
     controller
    0.38
    Activations Density 0.001%

    No Known Activations