© 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. 220236
    Prev
    Next
    INDEX
    Explanations

    presentations, collections, looking

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

    relationship, connection

    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
    PSW
    0.51
    arXiv
    0.51
     দু
    0.50
    müş
    0.50
     тільки
    0.49
    ayutt
    0.49
    𝚍
    0.49
    dü
    0.49
    はり
    0.49
    ＿
    0.48
    POSITIVE LOGITS
    弹
    0.45
     do
    0.44
     vision
    0.44
    彈
    0.44
     Dean
    0.44
     for
    0.44
     vocal
    0.43
     tenor
    0.43
     sockfd
    0.42
     demonstrations
    0.42
    Activations Density 0.000%

    No Known Activations