© 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. 1438
    Prev
    Next
    INDEX
    Explanations

    operating systems

    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
    ק
    1.87
    да
    1.84
    াদ
    1.76
    ка
    1.64
    اً
    1.51
    д
    1.41
    по
    1.38
    ೋ
    1.38
    烃
    1.38
    centrum
    1.33
    POSITIVE LOGITS
    ure
    1.68
    emptive
    1.58
    it
    1.48
    le
    1.44
    ला
    1.38
    aren
    1.34
    altering
    1.31
    ergic
    1.30
    дно
    1.27
    levard
    1.27
    Activations Density 0.009%

    No Known Activations