© 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. 60981
    Prev
    Next
    INDEX
    Explanations

    throw all

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

    quantities and qualifiers

    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
    맺
    0.46
    эй
    0.45
    relationships
    0.45
    สห
    0.43
    pering
    0.42
    establishing
    0.42
    व्यवस्था
    0.41
    seeking
    0.41
    ී
    0.41
    alignment
    0.41
    POSITIVE LOGITS
     كتير
    0.50
     teilweise
    0.50
     বাড়তি
    0.48
     Trol
    0.48
     Come
    0.47
     ziemlich
    0.47
     വരുന്ന
    0.47
     кілька
    0.47
     বিনাম
    0.47
    చ్చ
    0.46
    Activations Density 0.000%

    No Known Activations