© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40740
    Prev
    Next
    INDEX
    Explanations

    everyone makes mistakes

    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
     hiç
    1.10
     korral
    0.99
     escolas
    0.99
     múltiples
    0.95
    ::::::::::::::::
    0.94
     wszel
    0.94
     ഒന്നും
    0.93
     chó
    0.92
     sólo
    0.91
     खर्चा
    0.91
    POSITIVE LOGITS
    0.94
    Everyone
    0.84
    在這
    0.84
     Everyone
    0.84
    事項
    0.83
     Chemistry
    0.82
     thermoplastic
    0.82
    。
    0.82
     phenomena
    0.82
    ('
    0.79
    Activations Density 0.090%

    No Known Activations