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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7938
    Prev
    Next
    INDEX
    Explanations

    reports, fibers, sounds, pictures, letters, germs, rooms

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

    categories after common words

    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_53_width_65k_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
    :]:
    0.46
    ється
    0.44
    glie
    0.40
    峡
    0.36
    ется
    0.35
    贯
    0.35
    สุข
    0.34
    跪
    0.34
     quale
    0.34
    িত্যক্ত
    0.34
    POSITIVE LOGITS
     are
    0.47
    were
    0.41
     coseno
    0.41
     прошли
    0.39
    kog
    0.39
     бывают
    0.38
    itek
    0.38
     were
    0.38
     disperse
    0.38
    omely
    0.38
    Activations Density 0.000%

    No Known Activations