© 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. 26510
    Prev
    Next
    INDEX
    Explanations

    the book, the Company

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

    explaining an assessment

    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
    经常
    0.45
    陶
    0.44
    T
    0.43
    Ｔ
    0.41
    ，
    0.41
    盛
    0.40
    EURO
    0.40
    升
    0.40
    D
    0.40
    Vul
    0.39
    POSITIVE LOGITS
    mprj
    0.54
    𝘯
    0.50
     Бүген
    0.49
     सर्वात
    0.49
     വെ
    0.48
    assistance
    0.47
    animations
    0.47
     Бүгенге
    0.47
     assistants
    0.46
    addAnimation
    0.46
    Activations Density 0.000%

    No Known Activations