© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73422
    Prev
    Next
    INDEX
    Explanations

    technical defects or issues

    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
     for
    -0.88
    pageTitle
    -0.81
     major
    -0.81
     just
    -0.79
     at
    -0.79
     constantly
    -0.79
     as
    -0.78
     by
    -0.76
     other
    -0.76
     much
    -0.73
    POSITIVE LOGITS
    FFECT
    1.47
     affected
    1.31
    可能會
    1.20
    Affected
    1.10
    affected
    1.10
     incorrect
    1.10
    Incorrect
    1.06
     cirugía
    1.05
     determinadas
    1.05
     insufficient
    1.04
    Activations Density 0.017%

    No Known Activations