© 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. 16120
    Prev
    Next
    INDEX
    Explanations

    film and media references

    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
     who
    -1.13
    }\
    -1.09
     kabupaten
    -1.08
     objectAtIndex
    -1.08
     скриншот
    -1.05
     zamiast
    -1.02
     出演
    -1.02
     does
    -1.02
     system
    -0.99
    mrow
    -0.96
    POSITIVE LOGITS
     espé
    1.28
     sogar
    1.17
    licability
    1.16
     diverses
    1.14
    Curious
    1.11
    抬手
    1.09
     religieux
    1.09
     листь
    1.09
     여러
    1.08
     выпе
    1.06
    Activations Density 0.056%

    No Known Activations