© 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. 218666
    Prev
    Next
    INDEX
    Explanations

    introducing consequential words

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

    characterfaceused

    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
     chimneys
    0.50
     condos
    0.46
     samoglas
    0.46
    蚋
    0.45
    ाइट
    0.45
    ッ
    0.44
    roep
    0.44
     gif
    0.42
     swallowing
    0.42
    ਿ
    0.42
    POSITIVE LOGITS
     Reproduction
    0.50
    ésre
    0.48
    2
    0.46
    廂
    0.46
     Copies
    0.46
     Erik
    0.45
    benzoimidazol
    0.45
    ຄວາມ
    0.45
     Jamie
    0.44
    ដៃ
    0.44
    Activations Density 0.000%

    No Known Activations