© 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. 12977
    Prev
    Next
    INDEX
    Explanations

    G-ve bacteria, floorstrippers, currency symbols, brother names

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

    technical specifications and quantities

    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
    шения
    0.46
    ির
    0.45
     luego
    0.44
     আজাদ
    0.44
     forgets
    0.43
    🌷
    0.43
     endeav
    0.42
     }[
    0.42
     }],
    0.42
     Александра
    0.42
    POSITIVE LOGITS
    apad
    0.47
    速率
    0.46
     tempi
    0.45
    RIB
    0.45
    κι
    0.45
    ambahan
    0.44
    ΜΑ
    0.44
     usefulness
    0.44
    timepoint
    0.44
    HIB
    0.43
    Activations Density 0.000%

    No Known Activations