© 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. 122342
    Prev
    Next
    INDEX
    Explanations

    getting better

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

    Methods, USB, Automation, Mental, Physical

    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
    ب
    0.59
    ت
    0.58
    د
    0.53
    ل
    0.50
    স
    0.50
    ض
    0.50
    ینگ
    0.49
    ط
    0.48
    ز
    0.48
    لاسه
    0.48
    POSITIVE LOGITS
    ang
    0.54
    oliv
    0.52
    jir
    0.50
     yap
    0.48
     provoked
    0.47
     grpc
    0.47
     jit
    0.47
     concurs
    0.47
     ตัด
    0.47
     emphasis
    0.46
    Activations Density 0.000%

    No Known Activations