© 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. 15059
    Prev
    Next
    INDEX
    Explanations

    police arrive

    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
    п
    0.56
    et
    0.53
    νά
    0.50
    长
    0.50
    ба
    0.49
    longmapsto
    0.48
     Polymer
    0.48
    压缩
    0.47
    大
    0.47
    মাপ
    0.46
    POSITIVE LOGITS
     vain
    0.48
     menjaga
    0.44
     불
    0.43
     Byrd
    0.43
    usive
    0.42
     خون
    0.42
     भय
    0.41
     warrantless
    0.41
    vain
    0.41
     howling
    0.40
    Activations Density 0.004%

    No Known Activations