© 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. 163096
    Prev
    Next
    INDEX
    Explanations

    ISBN, Catholic, repair, Upload

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

    without performance degradation

    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
    從
    0.48
    branchNode
    0.46
     hört
    0.45
    ك
    0.44
    要因
    0.43
    。”
    0.43
    部門
    0.42
     evolve
    0.41
     spezial
    0.41
     पत्रों
    0.41
    POSITIVE LOGITS
    десь
    0.50
     наре
    0.46
    y
    0.45
    ொட
    0.44
    цев
    0.44
    ‌شده
    0.44
    ி
    0.44
     czyli
    0.44
    膊
    0.44
    зыва
    0.42
    Activations Density 0.000%

    No Known Activations