© 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. 64757
    Prev
    Next
    INDEX
    Explanations

    film production roles and awards

    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
    R
    -1.17
     verschiedenen
    -1.15
     our
    -1.14
    H
    -1.08
     time
    -1.02
     your
    -1.01
    Our
    -1.00
     verschiedene
    -0.99
    rimid
    -0.98
     U
    -0.98
    POSITIVE LOGITS
     queijo
    1.32
     maig
    1.31
    credited
    1.23
    sprodu
    1.23
    عاون
    1.20
     cebola
    1.20
    cheque
    1.20
     ché
    1.20
     maand
    1.19
    creating
    1.17
    Activations Density 0.016%

    No Known Activations