© 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. 3365
    Prev
    Next
    INDEX
    Explanations

    contrast or qualification

    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
    те
    0.80
     protrusions
    0.77
     expeditions
    0.77
     exacerb
    0.76
     interestingly
    0.76
     infestations
    0.75
    也
    0.73
     cultivars
    0.73
     oddly
    0.73
     tarn
    0.73
    POSITIVE LOGITS
    ’
    0.86
    ם
    0.75
    baixo
    0.75
    ć
    0.73
    ks
    0.73
     Реги
    0.72
    čiau
    0.71
    roga
    0.71
     Sementara
    0.70
    니
    0.70
    Activations Density 0.000%

    No Known Activations