© 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. 56659
    Prev
    Next
    INDEX
    Explanations

    Florence Hartmann

    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
    Negative Logits
    nik
    -0.85
     tup
    -0.75
     in
    -0.75
     O
    -0.75
    jo
    -0.74
     subtilis
    -0.72
    تهى
    -0.71
    jö
    -0.70
     душа
    -0.70
     Metab
    -0.70
    POSITIVE LOGITS
    のだろうか
    0.94
    ampire
    0.84
    dicion
    0.81
     alimenti
    0.79
    Inhalation
    0.78
     reemplazo
    0.77
    SharedCtor
    0.76
     miesto
    0.76
    Formulation
    0.76
     ukry
    0.74
    Activations Density 0.001%

    No Known Activations