© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47774
    Prev
    Next
    INDEX
    Explanations

    time ranges

    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
     out
    -1.14
    metra
    -0.82
     réservés
    -0.76
    ческая
    -0.75
    комнат
    -0.75
    عل
    -0.74
    },{
    -0.72
    ДУ
    -0.70
    ◠
    -0.70
     insumos
    -0.69
    POSITIVE LOGITS
    7
    0.88
    EARLY
    0.82
     early
    0.82
     ravis
    0.81
    OVERALL
    0.78
    strated
    0.77
    lysm
    0.77
    6
    0.77
    comparing
    0.75
    펭
    0.75
    Activations Density 0.013%

    No Known Activations