© 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. 10254
    Prev
    Next
    INDEX
    Explanations

    permeability or interplay

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to permeability in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Each
    -2.72
     Currently
    -2.47
    蚯
    -2.45
     were
    -2.45
     tenían
    -2.44
     additions
    -2.42
    тся
    -2.38
    方も
    -2.38
    媄
    -2.36
     filthy
    -2.33
    POSITIVE LOGITS
     setuju
    2.78
    ).
    2.75
    鼉
    2.61
    0
    2.59
     huiles
    2.58
     mengakui
    2.52
    霂
    2.52
    是没有
    2.52
     was
    2.50
     δεν
    2.48
    Activations Density 0.016%

    No Known Activations