© 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. 20436
    Prev
    Next
    INDEX
    Explanations

    clarify, specification, limitation

    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
     senza
    -1.38
     Consider
    -1.30
    rierte
    -1.25
     salud
    -1.23
    着一
    -1.22
    ancers
    -1.19
    ﺒ
    -1.17
     durante
    -1.16
    кога
    -1.16
    Durante
    -1.15
    POSITIVE LOGITS
     how
    1.66
    7
    1.43
     bahkan
    1.40
    ‴
    1.36
     roligt
    1.34
     further
    1.33
     each
    1.32
     giyim
    1.31
     why
    1.30
     avulla
    1.30
    Activations Density 0.084%

    No Known Activations