© 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. 117230
    Prev
    Next
    INDEX
    Explanations

    Spanish and technical queries

    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
     transmissão
    -0.86
    OTROS
    -0.84
    ární
    -0.84
    beu
    -0.80
     sanitarios
    -0.79
     décisions
    -0.79
    SALUD
    -0.78
    trer
    -0.78
    Shortcut
    -0.77
    Ḱ
    -0.77
    POSITIVE LOGITS
    érc
    0.87
    moveToFirst
    0.84
    까지
    0.79
     personally
    0.78
    ւ
    0.77
     disminuir
    0.77
    ágeno
    0.76
     purchases
    0.76
     indicated
    0.75
     WhatsApp
    0.75
    Activations Density 0.014%

    No Known Activations