© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124066
    Prev
    Next
    INDEX
    Explanations

    start of error or configuration messages

    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
     also
    -1.84
     a
    -1.72
     beispielsweise
    -1.49
     those
    -1.48
    也
    -1.45
     Präsident
    -1.44
     například
    -1.42
     interestingly
    -1.42
    。】
    -1.41
     actually
    -1.38
    POSITIVE LOGITS
     unless
    1.82
     jeżeli
    1.73
    icating
    1.67
    5
    1.57
     jeśli
    1.57
    ратор
    1.55
     because
    1.53
    ícia
    1.49
    peka
    1.47
    ícias
    1.46
    Activations Density 0.005%

    No Known Activations