© 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. 130632
    Prev
    Next
    INDEX
    Explanations

    supported by, monitored online, will then

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

    SQL Common Table Expressions

    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
     bedeut
    0.42
     neoplasms
    0.42
     hatta
    0.42
     ();
    0.41
    Accelerometer
    0.40
     prede
    0.40
    arse
    0.40
    िकुलर
    0.39
     atau
    0.39
     incorpor
    0.39
    POSITIVE LOGITS
    地理
    0.46
    萛
    0.44
    ério
    0.43
    为止
    0.41
    ȧ
    0.41
    ナ
    0.40
    ）【
    0.40
     যৌথ
    0.39
     Family
    0.39
    ibilité
    0.39
    Activations Density 0.000%

    No Known Activations