© 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. 6001
    Prev
    Next
    INDEX
    Explanations

    gentle actions

    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
    ні
    2.11
    ن
    2.02
    ны
    1.84
    स
    1.84
    ق
    1.80
    িক
    1.70
    n
    1.69
    ным
    1.65
    lari
    1.65
    ный
    1.64
    POSITIVE LOGITS
    jším
    1.84
    ῴ
    1.84
    jší
    1.80
    ce
    1.79
    cs
    1.57
    cito
    1.52
    ่
    1.51
     পাকিস্ত
    1.50
    ofthe
    1.49
    否
    1.49
    Activations Density 0.238%

    No Known Activations