© 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. 1527
    Prev
    Next
    INDEX
    Explanations

    subject, gradient, eigen, cardio, hier, sed

    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
    ों
    1.52
    ים
    1.36
    deki
    1.30
    㐄
    1.28
    ς
    1.27
    ्स
    1.26
    
    1.26
    ፍተኛ
    1.22
    $$_
    1.21
    ную
    1.20
    POSITIVE LOGITS
    ل
    1.55
    o
    1.28
    ש
    1.27
    ু
    1.26
    を確認
    1.22
     buk
    1.20
    ו
    1.20
    لین
    1.20
    Ы
    1.19
    šku
    1.17
    Activations Density 0.000%

    No Known Activations