© 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. 8085
    Prev
    Next
    INDEX
    Explanations

    includes what follows

    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
    م
    1.69
     accentuated
    1.58
    ৮
    1.53
     fittest
    1.50
    אי
    1.48
    اں
    1.48
    ని
    1.45
    म
    1.45
     atte
    1.41
    ﺮ
    1.39
    POSITIVE LOGITS
    2.13
    os
    1.86
    ad
    1.84
    us
    1.83
    ah
    1.82
    ut
    1.80
    teilung
    1.79
    at
    1.77
    ot
    1.76
    un
    1.76
    Activations Density 0.105%

    No Known Activations