© 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. 15578
    Prev
    Next
    INDEX
    Explanations

    actions or reasons

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

    Russian and Hebrew characters

    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
     the
    0.40
     restaurants
    0.39
    ↵↵
    0.37
     another
    0.35
    ).
    0.35
     hai
    0.35
     reduces
    0.35
     proporcional
    0.35
     use
    0.35
     increased
    0.35
    POSITIVE LOGITS
    Й
    0.51
    не
    0.50
    ול
    0.49
    ЛИ
    0.48
    ста
    0.47
    יו
    0.47
    В
    0.47
    א
    0.47
    ִ
    0.46
     அற்புதமான
    0.46
    Activations Density 0.042%

    No Known Activations