© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37064
    Prev
    Next
    INDEX
    Explanations

    O(n) complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     STUDENTS
    0.82
    ="")
    0.82
    PRIM
    0.80
    िटेशन
    0.79
    ámico
    0.77
    )،
    0.77
    StoredKeys
    0.76
     ﺍﻟ
    0.75
    ಮಾ
    0.75
     ".")
    0.75
    POSITIVE LOGITS
    י
    0.97
    Oe
    0.90
     of
    0.89
     lading
    0.88
    որ
    0.88
    that
    0.88
    llis
    0.88
    특별시
    0.88
     that
    0.87
     Somewhere
    0.86
    Activations Density 0.018%

    No Known Activations