© 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. 6881
    Prev
    Next
    INDEX
    Explanations

    time and thing

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

    injured herself, eventually reach, compatibilidade

    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
     전부
    0.56
    VII
    0.54
    öst
    0.53
    嶄
    0.53
     ملی
    0.50
    INI
    0.50
     اسلامی
    0.49
    akti
    0.49
     نئے
    0.49
    IEN
    0.49
    POSITIVE LOGITS
     organização
    0.45
     taux
    0.45
     ц
    0.44
     broke
    0.44
     CTL
    0.43
     fréquence
    0.43
     crimen
    0.43
     ダンロップ
    0.43
     traf
    0.43
     condição
    0.43
    Activations Density 0.000%

    No Known Activations