© 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. 108582
    Prev
    Next
    INDEX
    Explanations

    related to enabling, reducing, or ascending

    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
     منصوبہ
    0.53
    船舶
    0.50
    𝐗
    0.49
     автомобі
    0.49
    嘶
    0.49
     ০৯
    0.48
    ंबे
    0.48
    ध्
    0.48
    DBOutput
    0.48
     przechowy
    0.48
    POSITIVE LOGITS
    0.56
     (
    0.50
    (
    0.50
    ending
    0.46
    ..
    0.44
    tonic
    0.44
     n
    0.44
      
    0.43
     face
    0.42
     kale
    0.42
    Activations Density 0.000%

    No Known Activations