© 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. 6651
    Prev
    Next
    INDEX
    Explanations

    new repositories | different software

    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
    но
    0.67
    il
    0.59
    {
    0.58
    на
    0.57
    та
    0.56
    AL
    0.54
    너지
    0.54
    {'
    0.53
    "
    0.51
    ال
    0.50
    POSITIVE LOGITS
     sensação
    0.60
    ﺹ
    0.55
    绁
    0.52
    なった
    0.50
    回の
    0.49
    ர்களே
    0.49
     versão
    0.49
     CtApp
    0.48
     सीएचएसएल
    0.47
     fases
    0.47
    Activations Density 0.590%

    No Known Activations