© 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. 47231
    Prev
    Next
    INDEX
    Explanations

    copyright `rights` `conditions` `version`

    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
    álogos
    -0.94
    שלום
    -0.89
     hjälp
    -0.88
    voorbeeld
    -0.85
    rosin
    -0.84
    lainen
    -0.83
    Ή
    -0.83
    čni
    -0.82
    tende
    -0.82
     cytos
    -0.81
    POSITIVE LOGITS
     instead
    0.93
     considered
    0.84
     barely
    0.80
     mostly
    0.79
     it
    0.76
    ismo
    0.74
     where
    0.73
     if
    0.73
     around
    0.73
    هداف
    0.73
    Activations Density 0.001%

    No Known Activations