© 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. 62747
    Prev
    Next
    INDEX
    Explanations

    numbers following certain phrases

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

    dataframe operations and array manipulation

    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
     它
    0.57
     มัน
    0.48
     έναν
    0.46
     lanceol
    0.45
     όπου
    0.44
    ẫn
    0.43
     ৩০০
    0.43
     невероят
    0.43
     increíble
    0.42
     শতাব্দ
    0.42
    POSITIVE LOGITS
    зим
    0.51
    ቖ
    0.50
     moze
    0.47
    harm
    0.47
    if
    0.45
    Eyes
    0.45
    मेंट
    0.45
    StringSet
    0.44
    うち
    0.43
    subscribed
    0.43
    Activations Density 0.000%

    No Known Activations