© 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. 39818
    Prev
    Next
    INDEX
    Explanations

    Elephants

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

    foreign words and punctuation

    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
    h
    0.54
     coincident
    0.54
     endothelium
    0.47
     endothelial
    0.46
     transducer
    0.46
     preservation
    0.46
     Pontiac
    0.46
    HTC
    0.46
     தன்னை
    0.45
     preserved
    0.45
    POSITIVE LOGITS
    差別
    0.52
     комиссии
    0.51
    築
    0.51
     まず
    0.49
     metų
    0.49
     ادارے
    0.49
    誣
    0.48
     COURSE
    0.47
     წლის
    0.46
     แทน
    0.46
    Activations Density 0.000%

    No Known Activations