© 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. 88951
    Prev
    Next
    INDEX
    Explanations

    . followed by General or The

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

    air, brittle, lung capacity

    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
    에
    0.45
    ра
    0.42
    ؟!
    0.42
     혹은
    0.42
    원본
    0.42
    ോ
    0.42
     또는
    0.41
    Spo
    0.41
    inien
    0.41
    臤
    0.41
    POSITIVE LOGITS
     gradually
    0.51
     lur
    0.48
     lard
    0.46
     forn
    0.46
     Ryan
    0.45
     portraying
    0.45
     sloping
    0.44
     Zika
    0.44
     Airy
    0.44
    ໄ
    0.44
    Activations Density 0.002%

    No Known Activations