© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 888
    Prev
    Next
    INDEX
    Explanations

    soap note

    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
    т
    1.66
    ле
    1.62
    на
    1.61
    ן
    1.55
    俩
    1.55
    ा
    1.52
    ন
    1.52
    个
    1.46
    spedes
    1.44
    д
    1.44
    POSITIVE LOGITS
     idempot
    1.73
     peptid
    1.69
     governs
    1.52
     znak
    1.47
     benda
    1.46
     publice
    1.46
    HHHH
    1.45
    ﻛ
    1.42
     aval
    1.41
     QnrB
    1.41
    Activations Density 0.017%

    No Known Activations