© 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. 22-GEMMASCOPE-RES-131K
    7. 16693
    Prev
    Next
    INDEX
    Explanations

    setting configuration options

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Y
    -1.03
     Per
    -1.03
     ஒரு
    -1.02
    汕
    -0.99
    ın
    -0.98
    ginous
    -0.98
     Ar
    -0.98
     '*':
    -0.96
    니까
    -0.96
    Y
    -0.94
    POSITIVE LOGITS
    接著
    1.15
     będę
    1.12
     further
    1.09
     silnika
    1.07
     velocidade
    1.07
     nuest
    1.06
     Accesorios
    1.05
     Agreg
    1.03
    廝
    1.02
    uſ
    1.01
    Activations Density 0.007%

    No Known Activations