© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    remove whitespace or unwanted characters

    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
    頤
    0.46
    SWITCH
    0.46
    coupling
    0.40
    cosystem
    0.39
    allocation
    0.39
    ื
    0.39
    昌
    0.39
    ី
    0.38
    dynamical
    0.38
     vyu
    0.38
    POSITIVE LOGITS
     removing
    1.74
     remove
    1.73
     Remove
    1.71
     removes
    1.68
    Remove
    1.63
     Removing
    1.63
     Removes
    1.62
    去除
    1.61
    remove
    1.58
    Removing
    1.55
    Activations Density 0.046%

    No Known Activations