© 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. 34130
    Prev
    Next
    INDEX
    Explanations

    past states or conditions

    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
     convaincre
    -1.57
     bénéficier
    -1.57
     accompagner
    -1.56
    鶺
    -1.53
     siè
    -1.52
    龇
    -1.51
     occuper
    -1.49
     imprimer
    -1.43
     grijs
    -1.43
     téléph
    -1.42
    POSITIVE LOGITS
     had
    1.66
     get
    1.62
     so
    1.52
     dramatically
    1.52
     with
    1.50
     invigor
    1.45
     at
    1.40
     drastically
    1.39
     as
    1.38
     could
    1.36
    Activations Density 0.060%

    No Known Activations