© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60836
    Prev
    Next
    INDEX
    Explanations

    tolerable, unbearable, ability, bear

    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
     mág
    -2.52
    皷
    -2.38
    ㈮
    -2.31
    ⚋
    -2.28
     quadrinhos
    -2.28
    isation
    -2.28
    菹
    -2.28
     constater
    -2.25
    댔
    -2.25
    ㈪
    -2.19
    POSITIVE LOGITS
     que
    2.41
    .
    2.03
     in
    1.98
    ↵
    1.84
    ского
    1.82
    These
    1.80
     and
    1.76
    ים
    1.66
    that
    1.57
     even
    1.52
    Activations Density 0.004%

    No Known Activations