© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4271
    Prev
    Next
    INDEX
    Explanations

    scratch programming language

    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
    ت
    1.95
    没有
    1.74
    تون
    1.70
    تان
    1.66
    ມີ
    1.62
    ور
    1.61
    ੇ
    1.60
    تك
    1.59
    很多
    1.55
    面的
    1.53
    POSITIVE LOGITS
    a
    2.03
    c
    1.49
    こと
    1.48
     authorizes
    1.47
    cknowled
    1.46
    াতি
    1.45
     stunning
    1.41
    aat
    1.41
     linal
    1.39
    েয়
    1.38
    Activations Density 0.001%

    No Known Activations