© 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. 130732
    Prev
    Next
    INDEX
    Explanations

    title washing washes

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

    candidate would, lung, modular, recent, allegations

    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
     במהלך
    0.51
     kože
    0.50
     worsen
    0.48
     intérieure
    0.47
     ৭
    0.47
    中に
    0.47
    当天
    0.47
     utak
    0.46
    seven
    0.46
     cena
    0.46
    POSITIVE LOGITS
    ه
    0.55
     आल्सो
    0.51
    DES
    0.50
     antioxid
    0.48
    اه
    0.48
    чным
    0.47
    AZ
    0.45
     Aloha
    0.45
     immunotherapy
    0.45
    чными
    0.45
    Activations Density 0.000%

    No Known Activations