© 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. 480
    Prev
    Next
    INDEX
    Explanations

    common pairings and phrases

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

    units of measurement

    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
    لق
    0.52
    نق
    0.52
     Kaye
    0.48
    νας
    0.48
    нул
    0.48
     Eb
    0.47
    ד
    0.47
     autoimmunity
    0.47
    ช
    0.47
    થી
    0.46
    POSITIVE LOGITS
     세포
    0.55
    ˜</
    0.48
     poesía
    0.45
    ISSU
    0.45
     卡
    0.45
     网
    0.44
    coords
    0.44
     細胞
    0.44
     poesia
    0.43
     দক্ষ
    0.43
    Activations Density 0.000%

    No Known Activations