© 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. 99889
    Prev
    Next
    INDEX
    Explanations

    but clauses

    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
     autonomie
    -1.51
     idyl
    -1.44
    (*^^
    -1.40
    Vendo
    -1.31
    ＼(^
    -1.31
    回来的
    -1.30
    erráneo
    -1.28
     bluza
    -1.28
    놨
    -1.27
    SFER
    -1.26
    POSITIVE LOGITS
     because
    1.86
     .
    1.76
     since
    1.65
    ....
    1.42
    ..
    1.41
    |
    1.41
     so
    1.40
     it
    1.34
     \
    1.34
    U
    1.30
    Activations Density 0.040%

    No Known Activations