© 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. 77911
    Prev
    Next
    INDEX
    Explanations

    configuration options

    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
    پور
    -0.99
    机
    -0.90
    плика
    -0.82
    “[
    -0.82
    ophila
    -0.82
     oferta
    -0.80
     ROOMS
    -0.79
     proiz
    -0.79
     SCIENCES
    -0.78
     cient
    -0.78
    POSITIVE LOGITS
     affiliated
    0.78
     environment
    0.78
    Здесь
    0.74
     therefore
    0.74
     FAS
    0.71
     מע
    0.71
     up
    0.71
    しかも
    0.70
     assignments
    0.70
    ществует
    0.70
    Activations Density 0.021%

    No Known Activations