© 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. 65334
    Prev
    Next
    INDEX
    Explanations

    conflict and critique

    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
     some
    -1.55
     sometimes
    -1.48
     good
    -1.45
     then
    -1.41
     after
    -1.40
     how
    -1.40
     there
    -1.28
     may
    -1.28
     if
    -1.26
     maybe
    -1.25
    POSITIVE LOGITS
     télécommande
    1.38
     constater
    1.30
    continuing
    1.30
    hibits
    1.25
     FANT
    1.24
     équipements
    1.21
     auteurs
    1.20
     وزير
    1.19
    quested
    1.18
    responsible
    1.18
    Activations Density 0.023%

    No Known Activations