© 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. 72740
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    abaikan
    -1.23
    hasilkan
    -1.15
     will
    -1.14
    褙
    -1.09
     one
    -1.09
    Bonsoir
    -1.09
     into
    -1.08
     navigazione
    -1.08
     composizione
    -1.06
     makl
    -1.06
    POSITIVE LOGITS
     “
    1.31
    /">
    1.23
     siempre
    1.20
    !”
    1.18
     ‘‘
    1.16
     Dienstag
    1.15
    “(
    1.15
    』『
    1.13
     “(
    1.13
    ordinator
    1.09
    Activations Density 0.090%

    No Known Activations