© 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. 72123
    Prev
    Next
    INDEX
    Explanations

    NOT NULL constraints

    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
    埼玉
    -1.01
     as
    -1.01
     Abgerufen
    -0.90
     голове
    -0.90
    貸切
    -0.89
     because
    -0.88
    OOOO
    -0.88
     this
    -0.87
     squeeze
    -0.85
     muro
    -0.85
    POSITIVE LOGITS
     ráp
    1.10
    きら
    1.02
     côn
    1.00
     mít
    0.98
     Ă
    0.96
     lú
    0.93
     tôt
    0.92
     nieuwe
    0.92
     trám
    0.92
     áng
    0.91
    Activations Density 0.048%

    No Known Activations