© 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. 168701
    Prev
    Next
    INDEX
    Explanations

    words and punctuation

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

    while not

    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
     recoger
    0.52
    irlos
    0.49
     lla
    0.49
     revelar
    0.49
     उद्ध
    0.47
    ▟
    0.47
    owała
    0.47
    ва
    0.46
     pierws
    0.46
     predstavlja
    0.46
    POSITIVE LOGITS
    I
    0.56
    Email
    0.51
    Computational
    0.50
    Warm
    0.49
    Blessed
    0.48
    Angel
    0.48
    Routine
    0.48
    Pending
    0.47
    AIN
    0.47
    RTT
    0.47
    Activations Density 0.006%

    No Known Activations