© 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. 189691
    Prev
    Next
    INDEX
    Explanations

    Goodwill Industries, ATM machine, thanks for

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

    Ethernet interface, KS operates, systems and

    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
     標準
    0.51
    ismarck
    0.47
     ነ
    0.47
    iostream
    0.46
     እንዳ
    0.46
    佛教
    0.46
     ಲ
    0.46
     ដោយ
    0.45
     ವ್ಯಾ
    0.45
     くれ
    0.45
    POSITIVE LOGITS
    ан
    0.52
    का
    0.50
    гай
    0.48
     Eel
    0.47
    า
    0.47
     gigante
    0.46
    N
    0.46
     Animal
    0.46
     Sumo
    0.46
     pepe
    0.46
    Activations Density 0.000%

    No Known Activations