© 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. 112584
    Prev
    Next
    INDEX
    Explanations

    followed by context words

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

    Providing context or examples

    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
    ٨
    0.56
    মিক
    0.51
    exerc
    0.50
     чемпи
    0.50
    äjä
    0.50
    لها
    0.48
    assurer
    0.48
     испы
    0.48
    ляет
    0.48
    frü
    0.47
    POSITIVE LOGITS
     pos
    0.55
     as
    0.52
    0.52
     hali
    0.47
     ś
    0.45
     pristine
    0.44
     tiny
    0.44
     saucer
    0.44
     manicure
    0.44
     partidas
    0.44
    Activations Density 0.000%

    No Known Activations