© 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. 129417
    Prev
    Next
    INDEX
    Explanations

    global disruption and impact

    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
     when
    -1.41
     cuando
    -1.34
     their
    -1.34
     should
    -1.28
    :['
    -1.21
     siempre
    -1.17
     they
    -1.14
     actually
    -1.13
     only
    -1.10
     would
    -1.09
    POSITIVE LOGITS
    ATURES
    1.39
     worldwide
    1.13
     téléchargez
    1.12
    的模样
    1.10
     everywhere
    1.10
     flä
    1.09
     fidé
    1.08
     ผู้
    1.07
     spéciale
    1.06
     COLUMBIA
    1.06
    Activations Density 0.073%

    No Known Activations