© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9307
    Prev
    Next
    INDEX
    Explanations

    explains why or how

    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
     bengal
    -1.64
     vocale
    -1.59
     industrie
    -1.55
     ampoule
    -1.52
     cursus
    -1.52
     patate
    -1.49
     fatale
    -1.49
    桖
    -1.44
     rosso
    -1.44
    寶寶
    -1.42
    POSITIVE LOGITS
     how
    3.17
     why
    2.83
     where
    2.64
     what
    2.52
     the
    1.57
     dzięki
    1.54
     gdzie
    1.54
     dlaczego
    1.53
     haces
    1.51
     quando
    1.48
    Activations Density 0.121%

    No Known Activations