© 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. 23510
    Prev
    Next
    INDEX
    Explanations

    at the foot of the board

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

    taken in, Reusable rockets

    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
     Mitochondrial
    0.46
     Gambia
    0.45
    osan
    0.44
    5
    0.43
     Pleasant
    0.42
    7
    0.42
     Saudi
    0.42
     Proble
    0.42
     оказался
    0.41
    3
    0.41
    POSITIVE LOGITS
    制作
    0.44
     dashboards
    0.43
     ቀለም
    0.43
    次数
    0.42
     이미지
    0.42
    在线
    0.41
    सीना
    0.41
     ওয়েব
    0.41
    汇总
    0.41
    顶部
    0.41
    Activations Density 0.000%

    No Known Activations