© 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. 20031
    Prev
    Next
    INDEX
    Explanations

    possible outcomes

    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
    ?”
    -1.59
     unga
    -1.45
    });
    -1.44
    !
    -1.42
     prado
    -1.35
     novamente
    -1.33
     kaos
    -1.32
    ”)
    -1.32
    !”
    -1.30
    ?
    -1.28
    POSITIVE LOGITS
     a
    2.23
     such
    1.63
     vielfäl
    1.39
     špat
    1.37
     takiej
    1.35
     klassischen
    1.30
     verschieden
    1.29
    [
    1.28
     llanto
    1.28
     following
    1.24
    Activations Density 0.092%

    No Known Activations