© 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. 22-GEMMASCOPE-RES-131K
    7. 65602
    Prev
    Next
    INDEX
    Explanations

    computer interface abbreviations

    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_22/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
     the
    -1.49
     smrti
    -1.19
     obno
    -1.19
     Ár
    -1.17
     dangere
    -1.17
     ativ
    -1.14
     rús
    -1.12
     dentes
    -1.11
     extré
    -1.11
     Itália
    -1.09
    POSITIVE LOGITS
     is
    1.08
     pouze
    1.05
     compliant
    1.05
    withId
    1.03
     sahiptir
    1.02
     behe
    0.98
    roring
    0.98
    ômico
    0.98
     lediglich
    0.97
     folgende
    0.96
    Activations Density 0.178%

    No Known Activations