© 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. 76501
    Prev
    Next
    INDEX
    Explanations

    warning messages

    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
    🗹
    -1.13
    锒
    -1.00
    为您
    -0.99
    Ꮟ
    -0.97
     acheter
    -0.96
     poleg
    -0.95
    욤
    -0.95
     favoris
    -0.93
    дъ
    -0.92
    衪
    -0.92
    POSITIVE LOGITS
     Warning
    1.69
    ⚠️
    1.59
     warns
    1.52
     warning
    1.48
     caution
    1.43
    Warning
    1.30
     WARNING
    1.27
    );
    1.23
     warnings
    1.23
     Caution
    1.22
    Activations Density 0.015%

    No Known Activations