© 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. 10-GEMMASCOPE-RES-131K
    7. 84231
    Prev
    Next
    INDEX
    Explanations

    constructive feedback, criticism, alignment, measure

    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_10/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
     undangan
    -2.58
     advogado
    -2.53
     penerima
    -2.48
     rahasia
    -2.41
    其他
    -2.41
     dapatkan
    -2.41
    我真的
    -2.38
     pelaksanaan
    -2.36
     aprobó
    -2.34
     laporan
    -2.30
    POSITIVE LOGITS
    取り付け
    2.39
    $
    2.38
    髫
    2.34
    菒
    2.33
    あります
    2.23
    猛然
    2.14
    脔
    2.13
    镲
    2.09
    蕺
    2.09
    ’.
    2.08
    Activations Density 0.002%

    No Known Activations