© 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. 66081
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    遠い
    -1.07
    Hear
    -1.00
     garçons
    -0.98
     небо
    -0.97
    Hunting
    -0.96
    づけ
    -0.96
    えました
    -0.95
    多少钱
    -0.94
     derzeit
    -0.92
    چگونه
    -0.92
    POSITIVE LOGITS
     who
    1.59
     που
    1.23
     impecable
    1.21
    emore
    1.20
     vetores
    1.20
     砂
    1.18
    や
    1.16
    licitations
    1.14
     produisons
    1.13
     because
    1.13
    Activations Density 0.039%

    No Known Activations