© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 814
    Prev
    Next
    INDEX
    Explanations

    resource limits

    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
     Rept
    -0.81
    ടി
    -0.75
    zboi
    -0.73
    bals
    -0.71
     '');
    -0.70
     बु
    -0.69
     løpet
    -0.68
    Ax
    -0.68
     Lucian
    -0.68
     civile
    -0.67
    POSITIVE LOGITS
     Limits
    1.27
     limits
    1.25
     limit
    1.24
     resource
    1.17
    limits
    1.14
     Limit
    1.10
     limites
    1.05
     resources
    0.98
    Limits
    0.98
    limit
    0.97
    Activations Density 0.085%

    No Known Activations