© 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-16K
    7. 14746
    Prev
    Next
    INDEX
    Explanations

    action genre or description

    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_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
     Το
    2.23
    Το
    2.20
    ك
    2.00
    이기
    1.83
    gru
    1.78
    couch
    1.77
     digo
    1.74
    هما
    1.72
     İlç
    1.71
    dır
    1.70
    POSITIVE LOGITS
    يد
    1.90
    ak
    1.83
    oma
    1.75
    á
    1.75
    ikke
    1.73
    िक
    1.68
    í
    1.68
    ă
    1.62
    ри
    1.61
    ic
    1.56
    Activations Density 0.036%

    No Known Activations