© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200825
    Prev
    Next
    INDEX
    Explanations

    sales, purchase, availability, property

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

    especially those English requiring shape

    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
     sauvegard
    0.50
    )、
    0.46
    ),
    0.46
    ради
    0.46
    )}`;
    0.46
    トゥ
    0.45
    ة
    0.45
    aterdag
    0.44
    w
    0.43
     जरिए
    0.43
    POSITIVE LOGITS
     Universidade
    0.44
     Species
    0.43
    ೀರ
    0.43
     حاصل
    0.43
     stimulating
    0.43
    मित्व
    0.43
     그러면은
    0.43
     Thessaloniki
    0.42
    νονται
    0.42
    堊
    0.42
    Activations Density 0.002%

    No Known Activations