© 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. 190370
    Prev
    Next
    INDEX
    Explanations

    dangerously low

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

    Python interpreter

    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
     quilting
    0.44
    pinterest
    0.43
    咭
    0.42
    transpose
    0.42
    矢量
    0.42
    modeling
    0.42
    objet
    0.41
    egraphics
    0.41
     effectivement
    0.41
     carte
    0.41
    POSITIVE LOGITS
     Siempre
    0.52
     岩
    0.49
     Aufnahme
    0.49
     temprana
    0.48
    溜
    0.48
     開始
    0.48
     aumenta
    0.47
     Participate
    0.47
     Тому
    0.47
     Pla
    0.46
    Activations Density 0.000%

    No Known Activations