© 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. 80027
    Prev
    Next
    INDEX
    Explanations

    looking for

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

    purchases on

    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
    ק
    0.52
    ז
    0.52
    г
    0.51
    ד
    0.50
    חו
    0.49
    дер
    0.48
    ИН
    0.48
    ג
    0.48
    т
    0.47
    רי
    0.47
    POSITIVE LOGITS
     from
    0.41
     ion
    0.38
     của
    0.37
     Myanmar
    0.37
     for
    0.36
     {
    0.35
     i
    0.35
     https
    0.35
     website
    0.35
     December
    0.35
    Activations Density 0.276%

    No Known Activations