© 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. 47608
    Prev
    Next
    INDEX
    Explanations

    recommendations and conditions

    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
    Their
    -1.41
    <0xE1>
    -1.40
    almost
    -1.36
    described
    -1.33
    냑
    -1.32
    　　《
    -1.31
    こんばん
    -1.30
    瞜
    -1.30
     feront
    -1.29
    usually
    -1.28
    POSITIVE LOGITS
     with
    1.75
     more
    1.53
     any
    1.48
     in
    1.45
     which
    1.41
     such
    1.41
     this
    1.38
     or
    1.36
     to
    1.34
     for
    1.31
    Activations Density 0.096%

    No Known Activations