© 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. 69917
    Prev
    Next
    INDEX
    Explanations

    authorship and specific entities

    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
     connus
    -2.56
    中心的
    -2.41
    曩
    -2.36
    Rptr
    -2.31
    四月
    -2.28
     relentlessly
    -2.28
    enterOuterAlt
    -2.17
     wholly
    -2.16
    ﾀ
    -2.16
     perpetually
    -2.13
    POSITIVE LOGITS
     hervor
    2.53
    {
    2.50
    ↵↵
    2.48
    2.47
     ‘’
    2.47
    i
    2.31
    乆
    2.28
    remain
    2.28
     aktive
    2.23
     \
    2.17
    Activations Density 0.015%

    No Known Activations