© 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. 120815
    Prev
    Next
    INDEX
    Explanations

    asked for

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

    This text discusses

    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
    的风
    0.52
    纤
    0.44
     flexibles
    0.43
     moles
    0.43
    杀
    0.41
    随时
    0.40
     randomized
    0.40
     trecut
    0.40
     dual
    0.39
     газо
    0.39
    POSITIVE LOGITS
    hatiti
    0.54
    ইডি
    0.52
    ნიშვნ
    0.51
    haram
    0.50
    punctuation
    0.49
    classteacher
    0.48
    müş
    0.48
    ä
    0.48
    PLE
    0.48
    haro
    0.47
    Activations Density 0.001%

    No Known Activations