© 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. 244936
    Prev
    Next
    INDEX
    Explanations

    click save or download

    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
    nå
    0.48
    ρέπει
    0.45
    。
    0.45
    ньої
    0.43
    simx
    0.43
    量
    0.43
     victorious
    0.43
    utti
    0.42
    。\
    0.41
    和
    0.41
    POSITIVE LOGITS
     הולנד
    0.57
     جدید
    0.54
     חד
    0.52
     மஹ
    0.50
     სხვა
    0.49
     peony
    0.49
     orchards
    0.48
     زی
    0.46
    셜
    0.46
     아름
    0.45
    Activations Density 0.000%

    No Known Activations