© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4798
    Prev
    Next
    INDEX
    Explanations

    wear and tear

    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
    ل
    2.23
    ت
    1.77
    ج
    1.64
    acción
    1.59
    etään
    1.59
    ką
    1.55
    kę
    1.53
    ээр
    1.53
    дже
    1.51
    på
    1.49
    POSITIVE LOGITS
     $\{\
    1.61
     wardrobes
    1.53
    ০০০
    1.48
     roofs
    1.45
     berths
    1.44
     closets
    1.43
     ObjectMapper
    1.38
     conjunta
    1.38
     ales
    1.35
     overlying
    1.35
    Activations Density 0.000%

    No Known Activations