© 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. 200155
    Prev
    Next
    INDEX
    Explanations

    browser then

    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
    約
    0.50
     सुंदर
    0.48
     सौंदर्य
    0.46
    共
    0.45
     فريق
    0.45
     recordó
    0.44
    省
    0.44
    حضرت
    0.44
    禦
    0.44
    選擇
    0.44
    POSITIVE LOGITS
     reforms
    0.55
     howl
    0.53
     aceea
    0.48
     rate
    0.48
     spike
    0.46
     wink
    0.46
     acest
    0.46
     intervene
    0.46
     acela
    0.46
     cut
    0.45
    Activations Density 0.003%

    No Known Activations