© 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. 137945
    Prev
    Next
    INDEX
    Explanations

    business and product descriptions

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

    technically refers to, within, question words

    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
    为什么
    0.47
     hữu
    0.46
     Middleware
    0.45
    ací
    0.45
    ông
    0.44
    券
    0.44
     ContentView
    0.44
     DURING
    0.43
    緖
    0.43
     Yukawa
    0.43
    POSITIVE LOGITS
    as
    0.56
    and
    0.52
    instrument
    0.49
    instruments
    0.49
    often
    0.46
     afstand
    0.46
    precipitation
    0.45
     முறையில்
    0.45
    pink
    0.45
     दायर
    0.44
    Activations Density 0.001%

    No Known Activations