© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8356
    Prev
    Next
    INDEX
    Explanations

    number followed by of or file or data

    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
     its
    -1.63
    Its
    -1.51
    -1.44
     каждого
    -1.29
    By
    -1.25
    楽しめます
    -1.23
     può
    -1.22
    欸
    -1.22
    -1.20
    淪
    -1.20
    POSITIVE LOGITS
     using
    1.38
    〟
    1.25
     only
    1.21
     czerwca
    1.21
     definitely
    1.20
     発表
    1.20
     it
    1.17
     certainly
    1.15
     結
    1.15
    pesan
    1.14
    Activations Density 0.223%

    No Known Activations