© 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. 138320
    Prev
    Next
    INDEX
    Explanations

    provide equipment

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

    functions, actions, or processes

    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
     وهم
    0.48
    Tiene
    0.45
    ليو
    0.44
    :
    0.44
    ليات
    0.43
     Backbone
    0.43
     jüng
    0.42
    Tol
    0.42
     Ле
    0.41
     طريق
    0.40
    POSITIVE LOGITS
     stopwatch
    0.55
    ⿳
    0.50
     সম্মত
    0.45
    訨
    0.43
    ia
    0.43
     Americans
    0.43
    notepad
    0.43
    ঁর
    0.43
     clasificación
    0.42
    హం
    0.42
    Activations Density 0.002%

    No Known Activations