© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34514
    Prev
    Next
    INDEX
    Explanations

    `model` following `start_of_turn`

    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
    Negative Logits
     J
    0.70
     B
    0.66
     D
    0.63
     I
    0.56
     X
    0.55
     p
    0.54
     T
    0.54
    e
    0.54
     E
    0.53
     O
    0.53
    POSITIVE LOGITS
    ים
    0.81
    ات
    0.72
     that
    0.63
     që
    0.63
    ましたが
    0.63
    larından
    0.62
    ש
    0.62
    ുണ്ട്
    0.61
    ối
    0.60
    นั้น
    0.59
    Activations Density 0.569%

    No Known Activations