© 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. 15041
    Prev
    Next
    INDEX
    Explanations

    Lever on, Q:, The goal

    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
     even
    -1.44
     their
    -1.27
     on
    -1.16
     kupić
    -1.16
     its
    -1.16
     after
    -1.14
     immediately
    -1.13
     should
    -1.08
     these
    -1.08
     would
    -1.05
    POSITIVE LOGITS
    țele
    1.19
     ২০১
    1.16
     interessante
    1.09
    lería
    1.07
     bluetooth
    1.02
    みたいに
    1.01
     разных
    0.98
     еще
    0.98
     ergänzt
    0.98
    🏉
    0.97
    Activations Density 0.000%

    No Known Activations