© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229374
    Prev
    Next
    INDEX
    Explanations

    were written

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    خي
    0.53
    選擇
    0.50
     Emp
    0.48
     Mariah
    0.45
    Mama
    0.45
     EMS
    0.44
     Mujeres
    0.44
    >
    0.44
     Enlight
    0.44
    Doc
    0.44
    POSITIVE LOGITS
    indazole
    0.50
    attan
    0.43
     циф
    0.41
     народного
    0.41
    rictional
    0.41
    삵
    0.41
    яви
    0.40
    haften
    0.40
    putted
    0.39
    contribution
    0.39
    Activations Density 0.001%

    No Known Activations