© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6435
    Prev
    Next
    INDEX
    Explanations

    quoted text classification instruction

    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_16k_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
    這些
    0.78
    erat
    0.76
     oleh
    0.75
    你
    0.75
    但是
    0.75
    堊
    0.74
     मोहन
    0.74
     сега
    0.74
     ys
    0.73
    彥
    0.73
    POSITIVE LOGITS
    ix
    0.82
    ’
    0.79
    un
    0.78
    ,’
    0.75
    aluronic
    0.75
    доступ
    0.73
    irection
    0.70
    ів
    0.70
     consultations
    0.70
    liquidacion
    0.68
    Activations Density 0.001%

    No Known Activations