© 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. 74709
    Prev
    Next
    INDEX
    Explanations

    scheduled for, © copyright, img file

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

    profile vs. page

    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
    ِی
    0.52
    ဖ
    0.49
     بتاعتنا
    0.49
    ຣ
    0.49
     нашей
    0.47
    рных
    0.46
    ยี
    0.46
    раль
    0.46
    ъек
    0.45
    Megan
    0.45
    POSITIVE LOGITS
    scriptions
    0.50
    oggi
    0.49
     అమ్మ
    0.49
    s
    0.48
    agnar
    0.47
    ann
    0.46
    dz
    0.46
    em
    0.46
    dat
    0.46
    ario
    0.45
    Activations Density 0.000%

    No Known Activations