© 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. 35471
    Prev
    Next
    INDEX
    Explanations

    quantifying amounts

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

    who would win

    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
     ย
    0.45
    尟
    0.44
     พ
    0.44
    šť
    0.43
     relativement
    0.43
     навча
    0.43
     书
    0.43
     빙
    0.42
     trách
    0.42
     geheel
    0.42
    POSITIVE LOGITS
     overfitting
    0.57
     genomics
    0.49
     pathogenic
    0.49
     movements
    0.48
     pathogens
    0.47
     pathogen
    0.47
     orderBy
    0.46
     epigenetic
    0.46
    scapes
    0.46
     chimeric
    0.46
    Activations Density 0.000%

    No Known Activations