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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99906
    Prev
    Next
    INDEX
    Explanations

    prevent from

    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
     garantizar
    -0.98
     aldri
    -0.96
    ctia
    -0.92
    ޫ
    -0.88
     złotych
    -0.88
     garantia
    -0.87
    
    -0.84
     стара
    -0.84
     haunting
    -0.84
     aislamiento
    -0.84
    POSITIVE LOGITS
     from
    3.52
    from
    1.20
     desde
    1.17
     getting
    1.16
     от
    1.13
     nuo
    1.13
     från
    1.11
     From
    1.02
     từ
    1.02
     daripada
    1.02
    Activations Density 0.046%

    No Known Activations