© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18639
    Prev
    Next
    INDEX
    Explanations

    real numbers and mathematical spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    0.50
    rs
    0.47
    rl
    0.45
     灬
    0.45
    );
    0.44
     welds
    0.44
     confirms
    0.43
    ства
    0.43
    nc
    0.43
    ft
    0.42
    POSITIVE LOGITS
     mathematicians
    0.50
     Mathematik
    0.48
     pemrograman
    0.47
     racionais
    0.47
     vektor
    0.46
     Lexikon
    0.46
     moderne
    0.46
    ี
    0.46
    ณิต
    0.45
    یشنل
    0.45
    Activations Density 0.001%

    No Known Activations