© 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. 149516
    Prev
    Next
    INDEX
    Explanations

    Accepting states or activities

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

    accept risk, conservative estimate

    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
     abate
    0.50
    ѕ
    0.50
     pieds
    0.48
    ться
    0.46
     acknowledges
    0.44
     exuber
    0.44
     menggambarkan
    0.44
    abouts
    0.43
     ويع
    0.42
    hold
    0.42
    POSITIVE LOGITS
     aritmética
    0.48
    ສໍາ
    0.47
    ärt
    0.46
    સ્યા
    0.45
    赛
    0.45
    mán
    0.44
    笔者
    0.44
    一组
    0.43
     ગૃહ
    0.42
    ຄ້າ
    0.42
    Activations Density 0.001%

    No Known Activations