© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56965
    Prev
    Next
    INDEX
    Explanations

    symbols and foreign text

    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
     عسل
    -1.09
    回想
    -1.05
     territ
    -1.04
     stary
    -1.02
     mamy
    -1.00
    bisous
    -0.99
    Asimismo
    -0.97
     Ils
    -0.95
     helpt
    -0.94
     ofic
    -0.94
    POSITIVE LOGITS
     in
    0.89
    bairro
    0.87
     by
    0.85
    ceptre
    0.85
     /
    0.84
    疾患
    0.84
     stipulations
    0.84
    ัฒ
    0.84
    Hentet
    0.84
    ביוגרפיה
    0.83
    Activations Density 0.001%

    No Known Activations