© 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. 31-GEMMASCOPE-2-RES-262K
    7. 170024
    Prev
    Next
    INDEX
    Explanations

    tea ceremony or tea garden

    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_31_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
    Despite
    0.57
    اب
    0.50
    ());
    0.50
    Alger
    0.50
    กับ
    0.49
    Scottish
    0.48
    Animation
    0.47
    Everything
    0.47
    Inspired
    0.47
    Department
    0.47
    POSITIVE LOGITS
     accepting
    0.50
    ein
    0.49
     ब्रैकेट
    0.45
     잘못
    0.45
     mue
    0.45
     받
    0.44
     fuera
    0.44
     coaxial
    0.44
     interfaz
    0.44
    riba
    0.44
    Activations Density 0.002%

    No Known Activations