© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106393
    Prev
    Next
    INDEX
    Explanations

    actions or descriptions

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

    political campaign strategy

    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
    Negative Logits
     conserv
    0.47
    ówki
    0.45
    ⠀
    0.43
    ército
    0.43
     потер
    0.42
    筥
    0.42
     de
    0.42
    ోతి
    0.41
     resale
    0.41
     faithfulness
    0.41
    POSITIVE LOGITS
    jord
    0.44
     Animations
    0.43
    不禁
    0.42
    busy
    0.42
     Opens
    0.41
     প্রস্তাব
    0.41
    لس
    0.40
    fw
    0.40
     Hairst
    0.40
    ۗ
    0.39
    Activations Density 0.001%

    No Known Activations