© 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. 14177
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and states

    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
    七
    -1.47
    水
    -1.45
    有
    -1.41
    龙
    -1.38
    名称
    -1.38
    比特派
    -1.35
    ления
    -1.32
    ၀
    -1.32
     any
    -1.32
     more
    -1.29
    POSITIVE LOGITS
     of
    3.97
     that
    3.53
     they
    2.02
    事で
    1.56
     we
    1.50
    ところは
    1.48
    感じが
    1.48
    不好的
    1.45
     übri
    1.43
    為に
    1.42
    Activations Density 0.319%

    No Known Activations