© 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. 216764
    Prev
    Next
    INDEX
    Explanations

    foreign languages and scripts

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

    technical frameworks and abbreviations

    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
    i
    0.56
    n
    0.52
     carcass
    0.49
    做
    0.48
     leash
    0.47
    w
    0.46
     perro
    0.46
    洪
    0.46
     wund
    0.45
    u
    0.45
    POSITIVE LOGITS
     実
    0.55
     metų
    0.54
    -;
    0.53
     Մ
    0.52
    мітки
    0.51
     oznacza
    0.51
    -:
    0.49
     Чтобы
    0.48
     もの
    0.47
    äck
    0.47
    Activations Density 0.000%

    No Known Activations