© 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. 233128
    Prev
    Next
    INDEX
    Explanations

    tables, circles, payment, violence, muscle

    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
    ü
    0.58
    ówki
    0.53
    brains
    0.50
    <unused192>
    0.49
    ɰ
    0.49
    ን
    0.48
     soirée
    0.48
     នៅ
    0.48
    <start_of_turn>
    0.47
    followers
    0.47
    POSITIVE LOGITS
     berarti
    0.47
    及
    0.45
     Catalogue
    0.43
     time
    0.43
     числа
    0.41
     commodity
    0.41
     stance
    0.41
     Aboriginal
    0.41
     Time
    0.41
     ano
    0.41
    Activations Density 0.000%

    No Known Activations