© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    phrases describing entities or concepts

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

    options, drafts, prompts, tasks

    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
     ഒരു
    0.58
     τη
    0.57
     двох
    0.54
     управление
    0.53
    കേന്ദ്രം
    0.53
    󰀄
    0.52
     দুই
    0.52
     средство
    0.52
    lectricité
    0.51
    afety
    0.50
    POSITIVE LOGITS
    <strong>
    0.68
     pieces
    0.67
     goodies
    0.59
     contributors
    0.57
     articles
    0.56
     items
    0.55
     episodes
    0.51
     incarnations
    0.51
    -
    0.50
     accolades
    0.49
    Activations Density 0.590%

    No Known Activations