© 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. 152266
    Prev
    Next
    INDEX
    Explanations

    sequences indicating actions or states

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

    still be, contain, influence

    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
    нули
    0.52
     今回
    0.51
    𐱅
    0.51
     QuantityOnHand
    0.50
     対象
    0.50
    质疑
    0.49
     આરોપી
    0.49
    ørende
    0.48
    zeption
    0.48
    ürlich
    0.47
    POSITIVE LOGITS
    B
    0.47
     disappearing
    0.42
    ANDER
    0.42
    DIC
    0.41
    ರ್ಮ
    0.41
    ARK
    0.41
     wastes
    0.40
    LAN
    0.40
     washes
    0.40
    漫
    0.39
    Activations Density 0.001%

    No Known Activations