© 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. 10-GEMMASCOPE-RES-131K
    7. 101081
    Prev
    Next
    INDEX
    Explanations

    compilation albums, mixtape, PPV feed

    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
     bereits
    -1.73
     Even
    -1.70
     on
    -1.69
     well
    -1.44
     even
    -1.44
     eight
    -1.43
     даже
    -1.42
     навіть
    -1.41
    積極的に
    -1.30
     In
    -1.30
    POSITIVE LOGITS
     such
    1.73
    这样
    1.64
     houve
    1.54
    ごとの
    1.48
     dieß
    1.48
     carrito
    1.47
     kirim
    1.47
     cœurs
    1.44
     kuah
    1.42
     dinosaurio
    1.41
    Activations Density 0.170%

    No Known Activations