© 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. 84710
    Prev
    Next
    INDEX
    Explanations

    CRP, Pisces, FCS, Cyrus, Britannica

    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
    gucigalpa
    -2.59
    𖡼
    -2.56
    几个月
    -2.41
    恿
    -2.39
     manifests
    -2.36
     awful
    -2.34
     tujuh
    -2.33
     inquisitive
    -2.33
    0
    -2.28
    渽
    -2.27
    POSITIVE LOGITS
    o
    2.92
    ar
    2.84
    s
    2.53
    C
    2.44
    .
    2.44
    E
    2.30
    </i>
    2.13
    re
    2.13
    st
    2.11
     But
    2.02
    Activations Density 0.006%

    No Known Activations