© 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. 78458
    Prev
    Next
    INDEX
    Explanations

    foreign language titles and roles

    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
    Isabel
    -0.71
     sliding
    -0.71
     Klik
    -0.71
    beti
    -0.68
    破
    -0.68
    toggle
    -0.68
    もった
    -0.68
    colli
    -0.68
    udes
    -0.67
     opening
    -0.66
    POSITIVE LOGITS
    meester
    0.69
     ergeben
    0.68
    ilova
    0.66
     senador
    0.65
    брати
    0.63
     уси
    0.62
     siihen
    0.62
    ின்ற
    0.62
     можли
    0.62
    Baron
    0.62
    Activations Density 0.042%

    No Known Activations