© 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. 226250
    Prev
    Next
    INDEX
    Explanations

    tablet pc, keyboard festival, caveman

    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
    ని
    0.55
    രുവന
    0.49
     }}=\
    0.47
    这家
    0.46
    冰
    0.45
    仓
    0.44
    <footer>
    0.44
    ประสบการณ์
    0.44
    ও
    0.43
    Throughout
    0.43
    POSITIVE LOGITS
     fler
    0.52
     Coulomb
    0.48
     tablo
    0.48
     retouch
    0.47
     radian
    0.46
     SqlCommand
    0.46
     設計
    0.45
     glob
    0.44
     samar
    0.44
     होते
    0.44
    Activations Density 0.000%

    No Known Activations