© 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. 19628
    Prev
    Next
    INDEX
    Explanations

    though

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

    conjunction though

    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
    u
    0.96
    the
    0.95
    ี
    0.85
    ู
    0.80
    िंग
    0.75
    ാ
    0.73
    to
    0.71
    ী
    0.70
    า
    0.68
    тих
    0.66
    POSITIVE LOGITS
    在
    1.05
    '
    0.98
     in
    0.92
    ل
    0.91
    "
    0.81
    ス
    0.81
    你
    0.80
    Ι
    0.79
    ;
    0.76
    ため
    0.76
    Activations Density 0.022%

    No Known Activations