© 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. 10-GEMMASCOPE-RES-131K
    7. 45034
    Prev
    Next
    INDEX
    Explanations

    artist following dayton or jobs

    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_10/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
     voordat
    -1.92
     dacht
    -1.90
     wachten
    -1.87
     zonder
    -1.78
    Sự
    -1.72
     vertrouwen
    -1.67
     waarbij
    -1.63
     ontvangen
    -1.60
     trekken
    -1.60
     pozdě
    -1.59
    POSITIVE LOGITS
     a
    2.13
     it
    1.96
    er
    1.88
    」
    1.86
     they
    1.74
     other
    1.74
    但在
    1.73
     same
    1.69
     也
    1.68
    間の
    1.67
    Activations Density 0.008%

    No Known Activations