© 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. 31170
    Prev
    Next
    INDEX
    Explanations

    DOI and ISBN identifiers

    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
     their
    -1.01
     محفوظة
    -0.83
    unately
    -0.81
     through
    -0.81
    yasi
    -0.79
    скра
    -0.77
    Coy
    -0.74
    ря
    -0.74
    黩
    -0.73
     alam
    -0.72
    POSITIVE LOGITS
     unseren
    0.78
     pivot
    0.75
     HEL
    0.73
     כש
    0.73
    neas
    0.73
    TableBody
    0.73
     наших
    0.72
    omer
    0.72
     erhöht
    0.72
    OMO
    0.70
    Activations Density 0.012%

    No Known Activations