© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14906
    Prev
    Next
    INDEX
    Explanations

    doi links

    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_31_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
    heure
    0.54
    effect
    0.53
    ต้
    0.52
    צוני
    0.52
    h
    0.52
     Charley
    0.51
    hal
    0.49
     kh
    0.49
     kl
    0.49
     coordenadas
    0.48
    POSITIVE LOGITS
    bleday
    0.68
    当天
    0.64
    鸮
    0.61
    を得
    0.59
    سٹم
    0.57
    当时的
    0.55
    合わせ
    0.54
     электронной
    0.54
    援助
    0.54
    fdPar
    0.54
    Activations Density 0.003%

    No Known Activations