© 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. 88188
    Prev
    Next
    INDEX
    Explanations

    cooking instructions

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

    based on, shedding, latest, GPT

    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
     اهمیت
    0.48
     امن
    0.45
     stoichi
    0.45
    opardy
    0.45
    gaan
    0.44
    ؟
    0.44
    omania
    0.44
    gning
    0.44
     wichtigsten
    0.43
    ،
    0.43
    POSITIVE LOGITS
     Mex
    0.47
    спи
    0.46
     EXPL
    0.44
    SHADER
    0.42
    পিত
    0.42
     jugu
    0.41
    setCurrent
    0.41
    ச்செய
    0.41
     SCI
    0.40
     cual
    0.40
    Activations Density 0.003%

    No Known Activations