© 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. 38775
    Prev
    Next
    INDEX
    Explanations

    That's what

    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
    på
    1.15
    o
    1.09
    that
    1.09
    och
    1.08
    emer
    1.08
    ås
    1.08
    dington
    1.07
    directions
    1.06
    p
    1.06
    ról
    1.05
    POSITIVE LOGITS
     кстати
    1.45
     numerator
    1.35
    ಾರಿ
    1.33
    אי
    1.30
    淒
    1.30
     خاطر
    1.25
    к
    1.25
    芻
    1.25
    ない
    1.23
    ด้อ
    1.23
    Activations Density 0.020%

    No Known Activations