© 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. 66934
    Prev
    Next
    INDEX
    Explanations

    free time or breaks

    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
     they
    -1.81
     a
    -1.58
     the
    -1.38
    terus
    -1.34
     says
    -1.32
     sinyal
    -1.30
     if
    -1.26
     pertama
    -1.20
     professores
    -1.20
     that
    -1.18
    POSITIVE LOGITS
     =
    1.68
     vorigen
    1.48
    ).
    1.47
    ítimo
    1.45
     между
    1.36
    toje
    1.30
    ?).
    1.25
     zwischen
    1.25
     Seperti
    1.24
    Otras
    1.23
    Activations Density 0.030%

    No Known Activations