© 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. 60199
    Prev
    Next
    INDEX
    Explanations

    steps to complete a task

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

    expose

    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
    用に
    0.46
    𝕣
    0.45
     entsprechen
    0.38
    列表
    0.37
    向けの
    0.37
    上に
    0.36
    രുന്ന
    0.36
    "${
    0.36
    빴
    0.36
    ফাজ
    0.35
    POSITIVE LOGITS
    Submit
    0.60
     submit
    0.46
     Submit
    0.46
    submit
    0.46
     nút
    0.42
    ubmit
    0.42
     FLOR
    0.41
    ons
    0.39
     Publish
    0.39
    提交
    0.39
    Activations Density 0.013%

    No Known Activations