© 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. 145534
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, or medical symptoms

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

    buffering and threads

    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
     bhij
    0.53
    ay
    0.52
    婀
    0.51
    दि
    0.48
    anganan
    0.48
    agangan
    0.47
    ed
    0.46
    ccak
    0.46
    維持
    0.46
     Sald
    0.46
    POSITIVE LOGITS
     punishing
    0.49
     lượng
    0.47
     other
    0.45
     amounts
    0.45
    융
    0.45
    lander
    0.45
     carrot
    0.45
     rusty
    0.45
     tourists
    0.45
    мести
    0.44
    Activations Density 0.000%

    No Known Activations