© 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. 74165
    Prev
    Next
    INDEX
    Explanations

    items carried in bags or pockets

    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
    .《
    -1.25
    čeno
    -1.23
     APPELL
    -1.23
    casing
    -1.20
     Tentang
    -1.20
     lienzo
    -1.18
     Hvad
    -1.18
     peuples
    -1.18
    ņem
    -1.15
     COUNTRY
    -1.13
    POSITIVE LOGITS
     are
    1.78
    葙
    1.55
    ㉓
    1.53
    iliares
    1.44
     or
    1.31
     use
    1.29
    h
    1.28
    stdc
    1.27
    思議
    1.23
     וח
    1.23
    Activations Density 0.011%

    No Known Activations