© 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. 44226
    Prev
    Next
    INDEX
    Explanations

    phrases inside quotes or parentheses

    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
    ת
    0.96
    ان
    0.93
    ،
    0.86
    ามารถ
    0.85
     زیرا
    0.85
     مبنی
    0.83
     somit
    0.80
    ವಾಗಿರುತ್ತದೆ
    0.80
    륵
    0.79
    idlo
    0.79
    POSITIVE LOGITS
     utterance
    0.89
     তুমি
    0.88
    նել
    0.82
    you
    0.81
    (
    0.80
     тебя
    0.76
    ürgen
    0.76
    outro
    0.76
     तुमसे
    0.75
     তোমার
    0.75
    Activations Density 0.534%

    No Known Activations