© 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. 194761
    Prev
    Next
    INDEX
    Explanations

    parts of common phrases

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

    overall cycle, feel, latency, process

    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
    KY
    0.49
    키
    0.48
    政策
    0.46
    CPP
    0.46
    ENN
    0.45
    core
    0.45
    在
    0.45
    افي
    0.44
    في
    0.44
     continuously
    0.44
    POSITIVE LOGITS
     HUOBI
    0.52
     arrears
    0.50
     задачу
    0.50
     dė
    0.50
     ջ
    0.50
     radeon
    0.49
     αξ
    0.49
     हीट
    0.48
     пап
    0.48
    adás
    0.48
    Activations Density 0.000%

    No Known Activations