© 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. 105750
    Prev
    Next
    INDEX
    Explanations

    keywordscategoriesautomatically markedlike categoriesteeth duringwas shotprovides, in

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

    acidos, кислота

    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
     NASCAR
    0.46
    </u>
    0.45
    auml
    0.44
     RI
    0.44
    ORES
    0.44
     สม
    0.42
     CURRENT
    0.42
     crafting
    0.42
    設立
    0.41
     மேற்க
    0.41
    POSITIVE LOGITS
    bgColor
    0.54
     ácido
    0.48
    setRoi
    0.47
    앜
    0.47
    olli
    0.47
    막
    0.46
    考え
    0.45
     الجلد
    0.44
    当
    0.44
    ésus
    0.44
    Activations Density 0.000%

    No Known Activations