© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3282
    Prev
    Next
    INDEX
    Explanations

    foreign or political context

    np_acts-logits-general · gemini-2.5-flash-lite

    harm or discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     two
    0.46
     that
    0.45
    1
    0.42
     ત્રણ
    0.42
     three
    0.40
    3
    0.40
     этом
    0.40
     this
    0.40
    4
    0.40
    6
    0.39
    POSITIVE LOGITS
     políticos
    0.50
     altri
    0.48
     społecz
    0.45
     político
    0.44
     politische
    0.44
     działania
    0.42
     criminality
    0.42
     politici
    0.41
     دیگر
    0.41
     další
    0.41
    Activations Density 0.087%

    No Known Activations