© 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. 97369
    Prev
    Next
    INDEX
    Explanations

    choosing to do

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

    improve, risk, contaminate, I

    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
    奂
    0.47
    Мы
    0.47
     Yeast
    0.47
    XK
    0.46
    께
    0.45
    ছাই
    0.45
    identifier
    0.44
     Най
    0.44
     Nielsen
    0.43
     tyle
    0.43
    POSITIVE LOGITS
    まま
    0.45
    луу
    0.41
    теше
    0.41
    のです
    0.40
    ulously
    0.39
    ますが
    0.39
     bequeathed
    0.39
    गज
    0.37
     విజ
    0.37
    ]]),
    0.37
    Activations Density 0.000%

    No Known Activations