© 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. 69457
    Prev
    Next
    INDEX
    Explanations

    quantities and specifications

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

    monitoring remote patient

    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
     //{
    0.51
     INKA
    0.49
     виконання
    0.49
     Ikat
    0.46
     envisioned
    0.46
    生き
    0.46
     ITER
    0.45
     ARR
    0.45
     возгла
    0.43
     voluptas
    0.43
    POSITIVE LOGITS
    clock
    0.51
    help
    0.49
    eri
    0.49
    h
    0.47
    don
    0.46
    demon
    0.46
    ani
    0.45
    ano
    0.45
    g
    0.45
    jim
    0.44
    Activations Density 0.000%

    No Known Activations