© 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. 41677
    Prev
    Next
    INDEX
    Explanations

    debates

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

    political debate

    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
    內
    0.48
    ᱟ
    0.42
    उ
    0.41
     추진
    0.41
    destino
    0.41
    推动
    0.40
    内
    0.40
    ㄥ
    0.39
    人を
    0.39
    ಢ
    0.38
    POSITIVE LOGITS
     moderators
    0.60
     debates
    0.57
     televised
    0.56
     moderator
    0.54
     viewers
    0.54
     mics
    0.52
     candidates
    0.51
     probes
    0.51
     audience
    0.51
     topics
    0.51
    Activations Density 0.031%

    No Known Activations