© 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. 159339
    Prev
    Next
    INDEX
    Explanations

    strategic business communications

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

    Shipper, Hub, Elara

    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
     Curved
    0.46
     $:
    0.46
     Qxa
    0.45
     পরা
    0.45
     pessoa
    0.45
     skilful
    0.44
     শ্রো
    0.44
     公式
    0.44
    পূর্বক
    0.44
     قوان
    0.43
    POSITIVE LOGITS
    icar
    0.51
    did
    0.50
    ött
    0.50
    า
    0.46
    Fan
    0.45
     방
    0.43
    êu
    0.43
    फेस
    0.42
    टी
    0.41
    auto
    0.41
    Activations Density 0.000%

    No Known Activations