© 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. 238771
    Prev
    Next
    INDEX
    Explanations

    Paul did

    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
    갑
    0.43
    வு
    0.43
    h
    0.42
    icida
    0.41
    n
    0.41
    翎
    0.41
     supernatural
    0.40
    iney
    0.40
    H
    0.40
    личи
    0.39
    POSITIVE LOGITS
    ponym
    0.50
    uparavant
    0.49
     حوالي
    0.49
     solito
    0.46
    いろんな
    0.45
    zechoslovakia
    0.44
     مختلفة
    0.44
    ション
    0.43
     মজা
    0.43
    分けて
    0.42
    Activations Density 0.000%

    No Known Activations