© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62318
    Prev
    Next
    INDEX
    Explanations

    alleged crimes

    np_acts-logits-general · gemini-2.5-flash-lite

    sudden or middle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    even
    0.47
    ร้อม
    0.45
    唿
    0.45
    烁
    0.43
    ங்கு
    0.42
    mallow
    0.42
    咛
    0.42
    ལ་
    0.42
    ቛ
    0.42
    钤
    0.42
    POSITIVE LOGITS
     DUI
    0.46
     CuSO
    0.43
     banheiro
    0.42
     bamboo
    0.42
     XVII
    0.42
     DDT
    0.42
    CET
    0.41
     сан
    0.41
     bureaucrats
    0.41
     okolic
    0.41
    Activations Density 0.000%

    No Known Activations