© 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. 133419
    Prev
    Next
    INDEX
    Explanations

    accessing technology

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

    finding truths, statistics, or classifications

    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
    幅広い
    0.57
    仮
    0.57
    昨年
    0.55
    得
    0.53
    紹介
    0.52
    味噌
    0.52
    何度
    0.51
     சுற்றி
    0.51
    事で
    0.50
    肉
    0.49
    POSITIVE LOGITS
     oman
    0.49
     delineation
    0.48
     روا
    0.47
     which
    0.46
     đèn
    0.46
     Needless
    0.46
     Long
    0.46
     Hole
    0.45
     budgeting
    0.45
     внесен
    0.44
    Activations Density 0.000%

    No Known Activations