© 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. 161985
    Prev
    Next
    INDEX
    Explanations

    security updates; certain consequences

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

    few days, initial shock

    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
     खराब
    0.47
    vole
    0.47
    בר
    0.46
     শেষের
    0.46
    បញ្ចប់
    0.46
     período
    0.44
    〉
    0.44
    <unused20>
    0.44
    ]/
    0.44
    <unused90>
    0.44
    POSITIVE LOGITS
    佘
    0.50
    히
    0.48
     combinations
    0.46
    s
    0.46
     Ops
    0.44
    ச்சார
    0.44
     ops
    0.43
    li
    0.43
     연락
    0.43
    小时候
    0.42
    Activations Density 0.000%

    No Known Activations