© 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. 6696
    Prev
    Next
    INDEX
    Explanations

    aspects of

    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
    EC
    1.57
    ड
    1.45
     μπο
    1.39
     Charger
    1.37
    tolerant
    1.35
    ﺩ
    1.35
    IFT
    1.34
    h
    1.34
     Ce
    1.30
    hyp
    1.30
    POSITIVE LOGITS
    ıyla
    1.74
    စိတ်အပိုင်း
    1.65
    ColorBit
    1.63
     nasel
    1.55
    ление
    1.54
    ırd
    1.52
    おり
    1.51
    зь
    1.51
    atás
    1.50
    ciendo
    1.49
    Activations Density 0.028%

    No Known Activations