© 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. 39106
    Prev
    Next
    INDEX
    Explanations

    months and dates

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

    questionable judgment

    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
     దృష్టి
    0.53
    Ꭸ
    0.50
     पशु
    0.48
     مرات
    0.48
    ubic
    0.46
     లె
    0.46
     منهج
    0.46
    نية
    0.46
     الشيطان
    0.46
    Ꮠ
    0.46
    POSITIVE LOGITS
     inked
    0.50
     May
    0.49
     gây
    0.47
    2
    0.45
     front
    0.45
     Jan
    0.45
     as
    0.45
     Jednak
    0.44
    ’
    0.44
     No
    0.44
    Activations Density 0.000%

    No Known Activations