© 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. 62284
    Prev
    Next
    INDEX
    Explanations

    contact details

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

    questioning sanity, memory, perception

    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
    else
    0.57
     склады
    0.50
    ö
    0.48
    ud
    0.47
    ag
    0.46
    ek
    0.46
    ដើម្បី
    0.46
    ol
    0.43
    ata
    0.43
    ribution
    0.43
    POSITIVE LOGITS
    面白い
    0.48
    特朗普
    0.47
     autoplay
    0.46
     Noticias
    0.45
     Journalism
    0.44
     TEXAS
    0.44
     news
    0.44
     EVERYTHING
    0.44
    姣
    0.43
     Obamacare
    0.43
    Activations Density 0.000%

    No Known Activations