© 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. 77004
    Prev
    Next
    INDEX
    Explanations

    Welcome to our

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

    list items, bullet points, and numbering

    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
    टेट
    0.52
    婍
    0.48
    廣場
    0.48
    حي
    0.46
     apuestas
    0.46
    來的
    0.46
     estabilidad
    0.45
    óso
    0.45
    隱
    0.45
    數學
    0.45
    POSITIVE LOGITS
    .
    0.49
    z
    0.46
    lak
    0.44
     пробе
    0.44
    นั้น
    0.44
    いつ
    0.43
     Somm
    0.43
    何度も
    0.42
     என்பதே
    0.42
     Bann
    0.41
    Activations Density 0.000%

    No Known Activations