© 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. 30539
    Prev
    Next
    INDEX
    Explanations

    fighting statistics

    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
    埒
    -0.92
     those
    -0.91
     this
    -0.88
     these
    -0.88
     nueve
    -0.82
     even
    -0.81
    Vox
    -0.79
     until
    -0.78
    kontroll
    -0.78
     what
    -0.78
    POSITIVE LOGITS
     不是
    1.08
    缡
    0.93
    做的
    0.88
     svého
    0.86
     eliminare
    0.85
     sò
    0.84
    泞
    0.83
    varande
    0.83
    」
    0.82
    ₤
    0.82
    Activations Density 0.002%

    No Known Activations