© 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. 4264
    Prev
    Next
    INDEX
    Explanations

    listing

    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
    to
    1.14
    忡
    1.12
    zeitig
    1.05
    ta
    1.03
     sulfides
    1.02
    ţional
    1.00
    tral
    1.00
    要是
    0.96
    trim
    0.96
     esophageal
    0.94
    POSITIVE LOGITS
    ان
    1.82
    ال
    1.80
    야
    1.73
    ی
    1.57
    ה
    1.56
    ন
    1.55
    ل
    1.55
    ड
    1.51
    ت
    1.47
    ו
    1.43
    Activations Density 0.185%

    No Known Activations