© 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. 198250
    Prev
    Next
    INDEX
    Explanations

    speaking with "our"

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

    convert all available resources

    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
     త
    0.54
     స్క
    0.52
     રાખ
    0.51
     streetlight
    0.50
     τρόπο
    0.50
     በር
    0.49
     الدولي
    0.49
     зону
    0.49
    给予
    0.49
     ሌ
    0.49
    POSITIVE LOGITS
    s
    0.61
     inc
    0.55
    صل
    0.55
     indem
    0.54
    ر
    0.54
    یس
    0.54
    ה
    0.54
    er
    0.53
    ES
    0.53
    class
    0.53
    Activations Density 0.000%

    No Known Activations