© 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. 84719
    Prev
    Next
    INDEX
    Explanations

    financial contexts and common followed words

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

    explaining what things are

    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
    違反
    0.51
     extremists
    0.49
    ピン
    0.47
     nanow
    0.47
     infrared
    0.46
    イー
    0.46
    کنش
    0.46
    ਚ
    0.45
     flywheel
    0.44
     motherboard
    0.44
    POSITIVE LOGITS
     =)
    0.46
    ঽ
    0.46
    馀
    0.45
    ak
    0.45
    icture
    0.44
     :)
    0.44
     sebag
    0.44
     வழங்கு
    0.43
     tutor
    0.43
     مرة
    0.43
    Activations Density 0.000%

    No Known Activations