© 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. 31171
    Prev
    Next
    INDEX
    Explanations

    European personal names

    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
    two
    -0.91
     by
    -0.89
    いただける
    -0.89
    文件的
    -0.86
    ภายใน
    -0.86
     "`
    -0.85
     pueblo
    -0.84
    一歩
    -0.84
     any
    -0.84
    立場
    -0.84
    POSITIVE LOGITS
    fried
    1.27
     Fotografía
    0.96
     meravigli
    0.94
     cerâmica
    0.90
    bert
    0.89
     étudier
    0.89
    Ugh
    0.88
    ことを
    0.88
     specifiche
    0.88
    jamin
    0.88
    Activations Density 0.062%

    No Known Activations