© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14342
    Prev
    Next
    INDEX
    Explanations

    at least

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

    at least

    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
    Л
    0.55
     accumulations
    0.54
     OCE
    0.54
    まさに
    0.53
     eigent
    0.53
    И
    0.52
     simplesmente
    0.52
     mittler
    0.50
     semplicemente
    0.50
     oscillations
    0.50
    POSITIVE LOGITS
    至少
    0.80
    পক্ষে
    0.77
     অন্তত
    0.71
     atleast
    0.70
     almeno
    0.69
    少なくとも
    0.68
     least
    0.64
     zumindest
    0.61
    >≥</
    0.59
     попыта
    0.57
    Activations Density 0.036%

    No Known Activations