© 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. 15579
    Prev
    Next
    INDEX
    Explanations

    cooking instructions step-by-step

    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
    口
    0.54
    ૪
    0.46
     乳
    0.45
     আৰু
    0.45
     ventre
    0.45
     vaginal
    0.45
     unip
    0.44
     humbled
    0.44
    ն
    0.44
     погру
    0.43
    POSITIVE LOGITS
    fasst
    0.46
     लीजिए
    0.44
     رموز
    0.43
     Combustion
    0.42
     Ordnance
    0.42
     تطبيقات
    0.42
    蘑
    0.42
    tta
    0.41
     Clash
    0.41
     Mushrooms
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.