© 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. 99010
    Prev
    Next
    INDEX
    Explanations

    future prospects and upgrades

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

    sun and Sol facts

    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
    进步
    0.52
    偖
    0.50
    冲击
    0.49
    电子商务
    0.47
     Hopefully
    0.47
     uman
    0.46
    每个人
    0.46
    apore
    0.46
    未來
    0.46
    ⵍ
    0.46
    POSITIVE LOGITS
     refused
    0.45
     layer
    0.44
     reef
    0.43
     refrain
    0.42
     unusually
    0.41
     swoich
    0.40
     ratio
    0.40
     roar
    0.40
     grep
    0.39
     rar
    0.39
    Activations Density 0.000%

    No Known Activations