© 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. 139489
    Prev
    Next
    INDEX
    Explanations

    time for an operating capacity

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

    your requirements

    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
    t
    0.69
    add
    0.52
    ari
    0.52
    h
    0.50
    a
    0.50
    sat
    0.50
    1
    0.49
    arti
    0.48
    orm
    0.48
    herin
    0.48
    POSITIVE LOGITS
     Hasil
    0.48
     ehemal
    0.48
     ক্লান্ত
    0.47
     dargestellt
    0.47
    žený
    0.47
    椃
    0.47
     মাসের
    0.47
     صفر
    0.47
     Elektrokhimiya
    0.46
     आईपीएस
    0.46
    Activations Density 0.001%

    No Known Activations