© 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. 57100
    Prev
    Next
    INDEX
    Explanations

    gift of all

    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
    Ny
    0.48
    Bs
    0.45
    Loc
    0.45
    Delivery
    0.44
    icul
    0.44
    0.44
    ৪
    0.44
    Cu
    0.42
    _)
    0.42
    Pentru
    0.42
    POSITIVE LOGITS
     Stirling
    0.51
     Cornwall
    0.51
     démon
    0.50
     Lancaster
    0.49
     وړاندوینې
    0.48
     ஹைட்
    0.48
    سات
    0.47
     Daunting
    0.47
    စိတ်အပိုင်း
    0.46
     考え
    0.46
    Activations Density 0.002%

    No Known Activations