© 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. 8689
    Prev
    Next
    INDEX
    Explanations

    output should consist 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
     источники
    0.89
     justamente
    0.88
     спраши
    0.86
    michael
    0.84
    }\\
    0.80
    comend
    0.80
     искать
    0.80
    íamos
    0.80
    intensity
    0.80
     протяжении
    0.79
    POSITIVE LOGITS
    岁
    0.91
    奥
    0.79
    苏
    0.77
    畜
    0.77
    巻き
    0.76
    会
    0.75
     pals
    0.73
    الن
    0.72
     myeloma
    0.72
    سی
    0.71
    Activations Density 0.000%

    No Known Activations