© 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. 234718
    Prev
    Next
    INDEX
    Explanations

    continuous attention

    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
    miktar
    0.63
    Jumlah
    0.55
    Quantidade
    0.54
    數量
    0.52
    giver
    0.52
    ambilan
    0.50
    Approval
    0.50
    🥋
    0.50
    𝗴
    0.50
    מה
    0.48
    POSITIVE LOGITS
     arch
    0.57
     United
    0.49
     Ivy
    0.49
     yarn
    0.49
     UIC
    0.48
     light
    0.47
     thin
    0.47
     triglyceride
    0.47
     Lotus
    0.46
     Great
    0.45
    Activations Density 0.000%

    No Known Activations