© 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. 151628
    Prev
    Next
    INDEX
    Explanations

    transport followed by words ending in movement or action

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

    non-english and technical terms

    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
     লোককে
    0.55
     officers
    0.47
     odio
    0.46
    吃饭
    0.45
    cesz
    0.43
    <unused17>
    0.43
    oggle
    0.43
     লোকের
    0.43
     makan
    0.43
     tankers
    0.42
    POSITIVE LOGITS
     quasi
    0.44
    Ḥ
    0.42
     JMJD
    0.42
    펫
    0.41
    pseud
    0.40
     ಪ್ರಮಾಣ
    0.40
     dpi
    0.39
     unmodified
    0.38
     D
    0.37
    ふわ
    0.37
    Activations Density 0.002%

    No Known Activations