© 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. 744
    Prev
    Next
    INDEX
    Explanations

    possess a trait/feature

    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
    ్‌
    1.66
    oooo
    1.66
    ০০
    1.53
    ્સ
    1.48
    ного
    1.46
    ва
    1.45
    勻
    1.41
    
    1.41
    可以
    1.40
     ràng
    1.40
    POSITIVE LOGITS
    ط
    2.58
    ことになる
    2.33
    Aloe
    2.30
    ث
    2.25
     estudi
    2.19
     diariamente
    2.11
    את
    2.05
    இந்த
    2.02
    および
    2.02
    д
    2.00
    Activations Density 0.021%

    No Known Activations