© 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. 57986
    Prev
    Next
    INDEX
    Explanations

    protest chants and signs

    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
    FieldError
    -0.87
    (|
    -0.85
    arder
    -0.84
    格
    -0.84
    tifiable
    -0.82
    wsze
    -0.82
    breviation
    -0.81
    insets
    -0.80
     подряд
    -0.80
     attainment
    -0.79
    POSITIVE LOGITS
     organizer
    1.56
     chants
    1.53
     speakers
    1.36
     slogans
    1.36
     chanting
    1.33
     chanted
    1.32
     organizers
    1.29
     chant
    1.27
     rally
    1.26
    organizer
    1.25
    Activations Density 0.065%

    No Known Activations