© 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. 89168
    Prev
    Next
    INDEX
    Explanations

    non-English text

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

    discovery and association

    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
    -
    0.62
    وار
    0.45
    tit
    0.44
    يم
    0.43
    :
    0.43
    j
    0.43
    ier
    0.42
    riche
    0.42
    ри
    0.41
    ير
    0.40
    POSITIVE LOGITS
     长
    0.55
     ठंडा
    0.53
     आवाज
    0.52
     государственный
    0.52
     موږ
    0.52
     संसार
    0.51
     दुनिया
    0.51
     ಪರ
    0.50
     উত্স
    0.50
     குர
    0.50
    Activations Density 0.000%

    No Known Activations