© 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. 116260
    Prev
    Next
    INDEX
    Explanations

    statement help, commitment, service status, grant, second

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

    includes both

    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
    的好
    0.47
     इच्छा
    0.45
     множество
    0.45
    Foster
    0.44
    軸
    0.44
    ୮
    0.44
     চলতে
    0.43
     اذ
    0.43
    銀
    0.43
     الشكل
    0.43
    POSITIVE LOGITS
     orthogonal
    0.47
     ultra
    0.46
     aprox
    0.45
     põh
    0.43
    தன
    0.43
     ulter
    0.43
    ार्‍या
    0.42
     inclu
    0.42
     Orleans
    0.41
     parametr
    0.41
    Activations Density 0.001%

    No Known Activations