© 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. 81248
    Prev
    Next
    INDEX
    Explanations

    based on previous or own work

    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
     still
    -0.82
     hablar
    -0.77
     for
    -0.76
    complexType
    -0.76
     perhaps
    -0.75
     in
    -0.74
     Before
    -0.72
     because
    -0.72
    те
    -0.72
     so
    -0.72
    POSITIVE LOGITS
    previously
    1.30
    Previously
    1.21
     ранее
    1.10
     previously
    1.10
    Previous
    0.95
    earlier
    0.93
    ideas
    0.93
    estes
    0.93
    viously
    0.91
     DISTINCT
    0.91
    Activations Density 0.006%

    No Known Activations