© 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. 43744
    Prev
    Next
    INDEX
    Explanations

    stockinette

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

    political and social concepts

    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
     is
    0.46
     ا
    0.40
    وار
    0.39
     in
    0.39
     .
    0.38
     س
    0.38
     ج
    0.38
     است
    0.38
     bullpen
    0.38
     on
    0.37
    POSITIVE LOGITS
    InnerText
    0.43
    𐰺
    0.43
     carinatis
    0.42
     విజ
    0.42
     барои
    0.42
    ър
    0.42
     философ
    0.42
     минера
    0.41
     POLITICAL
    0.41
    urètre
    0.40
    Activations Density 0.232%

    No Known Activations