© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3001
    Prev
    Next
    INDEX
    Explanations

    has * or faced

    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
    ната
    0.63
    p
    0.62
    ek
    0.61
    w
    0.61
    t
    0.59
     situés
    0.59
    u
    0.59
     seconds
    0.58
     breakpoints
    0.58
     scheda
    0.57
    POSITIVE LOGITS
     Помимо
    0.46
    กว่า
    0.46
    য়ের
    0.45
    год
    0.44
    Տ
    0.44
     生
    0.43
    󰡔
    0.42
    厰
    0.42
    für
    0.42
    堕
    0.41
    Activations Density 0.216%

    No Known Activations