© 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. 30056
    Prev
    Next
    INDEX
    Explanations

    untrue

    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
     Namen
    -0.88
     Turbine
    -0.83
     moneda
    -0.82
     Meditation
    -0.80
    ILDREN
    -0.78
    rítica
    -0.77
    роде
    -0.77
     Tower
    -0.77
     will
    -0.77
     oleh
    -0.76
    POSITIVE LOGITS
     untrue
    3.05
     incorrect
    2.64
     inaccurate
    2.28
     FALSE
    2.06
     false
    2.02
    FALSE
    1.91
     Incorrect
    1.88
    Incorrect
    1.82
    false
    1.78
     accurate
    1.71
    Activations Density 0.046%

    No Known Activations