© 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. 7909
    Prev
    Next
    INDEX
    Explanations

    track orders and progress

    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
    во
    1.94
    то
    1.82
    ला
    1.80
     tông
    1.68
    ot
    1.62
    েও
    1.60
    ב
    1.59
    ты
    1.55
     cạnh
    1.55
    𒀊
    1.55
    POSITIVE LOGITS
    }$).
    2.16
    有利于
    2.09
    ১৮
    1.97
    age
    1.90
     Tracer
    1.90
    蹤
    1.76
    ert
    1.75
    izes
    1.74
    }$
    1.73
     गौरतलब
    1.73
    Activations Density 0.099%

    No Known Activations