© 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. 87998
    Prev
    Next
    INDEX
    Explanations

    simple instructions, improve, travel, altitude

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

    based on key information

    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
     umfass
    0.54
     ท
    0.53
     ؛
    0.52
     tę
    0.50
    ifie
    0.49
     znacznie
    0.49
    но
    0.47
     Ausnahme
    0.47
     ブラ
    0.45
     tỉnh
    0.45
    POSITIVE LOGITS
    ####
    0.46
    交代
    0.46
    趔
    0.45
    Δ
    0.44
    topic
    0.43
    {%
    0.43
    ਡੇ
    0.43
    背景
    0.43
    入口
    0.43
    Как
    0.42
    Activations Density 0.001%

    No Known Activations