© 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. 48625
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    space, universe, speed

    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
    辫
    0.44
    Chinese
    0.42
     ডা
    0.40
    MySQL
    0.40
    mute
    0.40
    Russian
    0.39
    Hel
    0.39
     русской
    0.38
     বাংলায়
    0.38
    麝
    0.38
    POSITIVE LOGITS
     átomos
    0.54
     gobiernos
    0.46
    objeto
    0.44
     aventuras
    0.43
     nadie
    0.43
     سفر
    0.43
     affront
    0.42
     nobody
    0.42
    szág
    0.42
    ല്ല
    0.41
    Activations Density 0.001%

    No Known Activations