© 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-262K
    7. 3617
    Prev
    Next
    INDEX
    Explanations

    false or imagined circumstances

    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
    還可以
    0.61
     skip
    0.61
     podrán
    0.61
    気になる
    0.57
    }-\
    0.55
    pointer
    0.54
    /
    0.54
    扱う
    0.54
    掌握
    0.53
    }}{
    0.53
    POSITIVE LOGITS
     njima
    0.81
     őket
    0.79
    existent
    0.73
     tarses
    0.72
    ărat
    0.70
    実際
    0.69
     अस्तित्व
    0.69
     causada
    0.67
    तमंद
    0.66
    其實
    0.66
    Activations Density 0.000%

    No Known Activations