© 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. 112761
    Prev
    Next
    INDEX
    Explanations

    effective clean and unwanted items

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

    year and its context

    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
     qualifying
    0.44
     enumerable
    0.43
     person
    0.43
    рий
    0.43
    н
    0.43
    ാവുന്ന
    0.42
    bere
    0.42
     Evam
    0.42
     Requirements
    0.42
     CommandCenter
    0.41
    POSITIVE LOGITS
    欧
    0.59
     radiates
    0.53
     duże
    0.52
    チーム
    0.51
    ஸின்
    0.51
     نب
    0.50
     আদালতে
    0.49
    モ
    0.49
     বিশাল
    0.48
     Mav
    0.48
    Activations Density 0.000%

    No Known Activations