© 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. 72331
    Prev
    Next
    INDEX
    Explanations

    assigning or comparing values

    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
     télécharger
    -1.22
     encendido
    -1.18
     peindre
    -1.16
    Currently
    -1.16
     nettoyer
    -1.15
     éviter
    -1.13
     accéder
    -1.13
     négo
    -1.11
    рин
    -1.09
     imprimer
    -1.09
    POSITIVE LOGITS
     as
    1.58
     for
    1.37
     also
    1.30
     R
    1.24
     will
    1.23
     more
    1.19
     in
    1.13
     He
    1.13
    ha
    1.13
     was
    1.12
    Activations Density 0.001%

    No Known Activations