© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76113
    Prev
    Next
    INDEX
    Explanations

    temporal ranges

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

    dates and time ranges

    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
     rampant
    0.44
    від
    0.44
    ()==
    0.43
     booming
    0.42
    চিত্র
    0.42
    fabrik
    0.41
     gangster
    0.41
     জগতে
    0.41
    IKA
    0.40
     scavenger
    0.40
    POSITIVE LOGITS
     Spend
    0.45
     Desar
    0.42
     ы
    0.41
     Oc
    0.41
     九
    0.40
     intermittently
    0.40
     例えば
    0.40
     Occasionally
    0.40
     тези
    0.39
     கூடுதலாக
    0.39
    Activations Density 0.024%

    No Known Activations