© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4831
    Prev
    Next
    INDEX
    Explanations

    German nouns and adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    隼
    0.81
    ང་
    0.81
    條
    0.79
     GDPR
    0.78
     odont
    0.78
    нинг
    0.77
    ヒト
    0.76
    槑
    0.76
    את
    0.75
     ಕಾನೂ
    0.75
    POSITIVE LOGITS
     links
    0.79
     lack
    0.78
     عض
    0.76
    quets
    0.72
     mechan
    0.70
    өг
    0.69
    rand
    0.67
     schemas
    0.67
     rand
    0.65
    itations
    0.65
    Activations Density 0.052%

    No Known Activations