© 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. 34-GEMMASCOPE-RES-131K
    7. 2556
    Prev
    Next
    INDEX
    Explanations

    film release

    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_34/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
     sufrir
    -0.73
     when
    -0.73
     without
    -0.72
     continued
    -0.72
     use
    -0.72
     while
    -0.71
     caída
    -0.70
     playful
    -0.70
     frequently
    -0.69
     rugged
    -0.69
    POSITIVE LOGITS
     release
    1.41
    release
    1.29
     theaters
    1.25
    Release
    1.20
     releases
    1.20
     theater
    1.20
     released
    1.17
     Release
    1.16
    released
    1.16
     theatres
    1.13
    Activations Density 0.020%

    No Known Activations