© 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. 6103
    Prev
    Next
    INDEX
    Explanations

    social media posts and content

    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
    ী
    1.49
    窕
    1.46
    F
    1.43
    ય
    1.41
     áo
    1.41
    ED
    1.40
    Ñ
    1.40
    əri
    1.35
    Ў
    1.34
    ó
    1.32
    POSITIVE LOGITS
    as
    2.05
    id
    2.00
    지만
    1.71
    لي
    1.69
    f
    1.66
    a
    1.66
    ق
    1.59
    to
    1.58
    dır
    1.54
    สต์
    1.54
    Activations Density 0.007%

    No Known Activations