© 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. 117588
    Prev
    Next
    INDEX
    Explanations

    Boeing 737 MAX 8 shooter

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

    risky situations or outcomes

    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
    సై
    0.46
    ᱣ
    0.45
    heastern
    0.43
    <0x0D>
    0.43
    OX
    0.43
    accharide
    0.40
    Jo
    0.40
    indication
    0.40
    ’
    0.39
     attachment
    0.39
    POSITIVE LOGITS
     AutoML
    0.56
     entschieden
    0.54
     تصمیم
    0.51
     précédemment
    0.49
     аўтаматы
    0.48
     zufrieden
    0.48
     Angriff
    0.48
     Preserve
    0.47
     கொண்டனர்
    0.47
    一个新的
    0.47
    Activations Density 0.000%

    No Known Activations