© 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. 129338
    Prev
    Next
    INDEX
    Explanations

    advancement, individuals, motor, unlock

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

    line connecting

    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
    ituation
    0.48
    çado
    0.48
    introdu
    0.47
     Sarawak
    0.45
    anda
    0.45
    噂
    0.44
     Preis
    0.44
     aihe
    0.44
    urados
    0.43
    ამაშ
    0.43
    POSITIVE LOGITS
    缱
    0.48
    であろう
    0.46
    =[];
    0.45
    🕺
    0.44
     transporter
    0.44
     مطم
    0.42
     वाहत
    0.42
    要么
    0.42
    inous
    0.42
     déchets
    0.41
    Activations Density 0.000%

    No Known Activations