© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32535
    Prev
    Next
    INDEX
    Explanations

    zav, wave, zwie

    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
    琥
    -0.81
    قا
    -0.69
     przypadku
    -0.68
    ModelAttribute
    -0.68
    canon
    -0.67
    Cano
    -0.67
    両親
    -0.67
     ajustar
    -0.66
     Geller
    -0.66
    INTE
    -0.66
    POSITIVE LOGITS
     zav
    0.88
     suspend
    0.81
    回忆
    0.74
    CBD
    0.73
    зяй
    0.71
     remet
    0.70
    ods
    0.69
    ials
    0.69
    らせる
    0.69
    dov
    0.68
    Activations Density 0.021%

    No Known Activations