© 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. 242303
    Prev
    Next
    INDEX
    Explanations

    hospice Feeling

    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
     Biochim
    0.54
     catap
    0.50
    ل
    0.46
    的应用
    0.46
     Schwerpunkt
    0.46
    ל
    0.46
     FGD
    0.46
     Chum
    0.45
    ন্ত্র
    0.45
    вате
    0.45
    POSITIVE LOGITS
    kre
    0.49
    ty
    0.48
    ﺃ
    0.47
    ters
    0.47
    cr
    0.46
    ks
    0.46
    nel
    0.46
    ⮕
    0.46
    珐
    0.45
    caster
    0.44
    Activations Density 0.000%

    No Known Activations