© 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. 194594
    Prev
    Next
    INDEX
    Explanations

    very large

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

    dispatch police

    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
     daje
    0.47
    ières
    0.46
     zaji
    0.45
    𝔬
    0.44
     european
    0.43
    Mu
    0.43
    SystemService
    0.43
     fornisce
    0.42
     relais
    0.42
     substit
    0.42
    POSITIVE LOGITS
    помним
    0.52
     раствор
    0.50
    )$\
    0.47
    を変
    0.47
    irman
    0.47
    )$\\
    0.47
    ,\
    0.45
    )|\
    0.45
    的一部分
    0.45
    $.\\
    0.44
    Activations Density 0.002%

    No Known Activations