© 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. 57945
    Prev
    Next
    INDEX
    Explanations

    political parties

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

    labels and specific items

    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
     vektor
    0.46
     carico
    0.45
    ا۔
    0.45
     doğr
    0.44
    वय
    0.44
     মহান
    0.44
    ணு
    0.43
    ۔
    0.43
    ા
    0.42
    क्षिक
    0.42
    POSITIVE LOGITS
     Lieberman
    0.46
     પાર્ટી
    0.45
     locales
    0.44
    adakan
    0.43
     partidos
    0.43
     marking
    0.42
    parties
    0.41
     Decoration
    0.41
     Marking
    0.41
     annivers
    0.40
    Activations Density 0.000%

    No Known Activations