© 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. 15311
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
     and
    -1.66
    :
    -1.12
     or
    -1.09
     either
    -1.09
     и
    -1.02
     by
    -0.98
     ولاية
    -0.88
     several
    -0.88
    ......
    -0.88
    ....
    -0.86
    POSITIVE LOGITS
     respectively
    2.14
    respectively
    1.70
     respectivamente
    1.48
     respective
    1.34
     respectivos
    1.30
     соответственно
    1.24
     respectivement
    1.22
     respectivas
    1.16
    respective
    1.13
    Elő
    1.11
    Activations Density 0.029%

    No Known Activations