© 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. 100814
    Prev
    Next
    INDEX
    Explanations

    SD card storage

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

    direct or install

    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
    可以将
    0.50
    heets
    0.49
     brengen
    0.47
    輥
    0.46
    鏻
    0.46
    一开始
    0.45
    奐
    0.44
    >∕
    0.43
    ⺈
    0.43
     কমান্ডার
    0.43
    POSITIVE LOGITS
     respectivas
    0.48
    _
    0.45
     (-
    0.45
    AM
    0.43
    ってくる
    0.42
    idi
    0.41
     言っ
    0.40
    mu
    0.40
     ->
    0.40
     ...,
    0.40
    Activations Density 0.006%

    No Known Activations