© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31498
    Prev
    Next
    INDEX
    Explanations

    font faces and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wied
    -0.82
     connotations
    -0.73
     saisir
    -0.72
    Conf
    -0.72
     Menlo
    -0.71
     Abo
    -0.71
     ucha
    -0.71
     lâng
    -0.70
     kotlinx
    -0.70
     floppy
    -0.70
    POSITIVE LOGITS
    Сыртқы
    0.71
    برها
    0.70
    ценка
    0.67
    hau
    0.63
     overdose
    0.62
     Eri
    0.60
     action
    0.60
     maquillaje
    0.59
     power
    0.59
     Warbler
    0.58
    Activations Density 0.066%

    No Known Activations