© 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. 245656
    Prev
    Next
    INDEX
    Explanations

    specifications and concessions

    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
    ил
    0.60
    f
    0.55
    op
    0.54
    ic
    0.52
    uut
    0.50
    imp
    0.49
    utt
    0.48
    ﺻ
    0.47
    ере
    0.47
    óle
    0.47
    POSITIVE LOGITS
     +(
    0.47
     pneumoniae
    0.47
     isti
    0.47
     yī
    0.45
     &(
    0.45
     laik
    0.45
    自在
    0.44
     practition
    0.44
     iskol
    0.44
    理念
    0.43
    Activations Density 0.000%

    No Known Activations