© 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. 194573
    Prev
    Next
    INDEX
    Explanations

    reason why

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

    side of the lane

    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
    ativity
    0.54
    an
    0.52
    pers
    0.52
    ↵↵
    0.50
    et
    0.50
    nych
    0.48
    ik
    0.48
    navy
    0.47
    harmonic
    0.46
    ↵↵↵
    0.46
    POSITIVE LOGITS
     abordar
    0.61
     మేము
    0.56
     અમને
    0.52
     devemos
    0.52
     거예요
    0.52
     Bakın
    0.52
     potwier
    0.51
     聞い
    0.51
     Operand
    0.50
     aclar
    0.50
    Activations Density 0.001%

    No Known Activations