© 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. 11737
    Prev
    Next
    INDEX
    Explanations

    abbreviated words

    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
    a
    2.20
    r
    2.08
    ie
    1.98
    ל
    1.98
    al
    1.84
    man
    1.79
    k
    1.75
    lle
    1.72
    il
    1.71
    an
    1.60
    POSITIVE LOGITS
    藺
    1.67
     `:`,
    1.66
    ב
    1.59
    dır
    1.56
    ški
    1.55
     लेट्स
    1.53
    がたくさん
    1.52
    getImageFolder
    1.51
    乑
    1.48
    现实
    1.48
    Activations Density 0.001%

    No Known Activations