© 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. 51073
    Prev
    Next
    INDEX
    Explanations

    various languages

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

    connecting words followed by specifics

    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
     tirelessly
    0.47
     mnoho
    0.45
     sporadically
    0.44
    ...',
    0.42
     frequent
    0.42
    *,
    0.42
     katika
    0.41
    频繁
    0.41
    ¸
    0.41
     çeşitli
    0.40
    POSITIVE LOGITS
    ストラップ
    0.42
    原来的
    0.41
     औपचारिक
    0.40
    🤣🤣
    0.39
    akaranam
    0.39
     хотел
    0.38
    ringle
    0.38
     ಸ್ವಲ್ಪ
    0.37
     তুই
    0.37
    地面
    0.36
    Activations Density 0.000%

    No Known Activations