© 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. 83966
    Prev
    Next
    INDEX
    Explanations

    data availability or absence

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

    seeking meaningful data

    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
    Traité
    0.50
    astrous
    0.48
    あなたは
    0.47
    ר
    0.47
    z
    0.46
    バ
    0.46
    競
    0.46
    を確認
    0.45
    ხ
    0.45
    飲
    0.45
    POSITIVE LOGITS
     Lec
    0.51
     Centers
    0.49
     Registry
    0.49
     Mural
    0.48
     eğer
    0.48
     this
    0.47
     Chiropractic
    0.47
     Soo
    0.46
     Serum
    0.46
     Denim
    0.45
    Activations Density 0.001%

    No Known Activations