© 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. 157456
    Prev
    Next
    INDEX
    Explanations

    described as

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

    purple buds

    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
     سقوط
    0.48
    設備の
    0.46
     emergencies
    0.45
     낙
    0.44
    sendKeyDown
    0.43
     النظام
    0.43
     pooch
    0.41
     중요하다
    0.41
     البر
    0.41
    ᆭ
    0.41
    POSITIVE LOGITS
    л
    0.48
    ل
    0.47
    Ве
    0.47
    ிருஷ்
    0.46
     szabály
    0.46
     Barak
    0.46
    க
    0.46
     Schwartz
    0.45
    lı
    0.45
     conform
    0.45
    Activations Density 0.001%

    No Known Activations