© 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. 24-GEMMASCOPE-2-RES-262K
    7. 7519
    Prev
    Next
    INDEX
    Explanations

    and | all

    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_24_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
     jemand
    0.71
    。</
    0.65
     ਇੱਕ
    0.63
     ذریع
    0.59
     tenths
    0.59
     kişi
    0.59
    。
    0.59
    这一点
    0.59
     glimps
    0.58
     surname
    0.58
    POSITIVE LOGITS
     এবং
    0.86
     and
    0.81
     மற்றும்
    0.80
     и
    0.79
     और
    0.78
     جميع
    0.78
    所有的
    0.77
     всех
    0.77
     અને
    0.75
     all
    0.74
    Activations Density 0.000%

    No Known Activations