© 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. 190080
    Prev
    Next
    INDEX
    Explanations

    United Kingdom, liquid resin

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

    appreciate complexity and efficiency

    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
     tats
    0.45
     အတွ
    0.45
    <unused50>
    0.44
     hulk
    0.44
     balloons
    0.43
     tablo
    0.42
     auctioned
    0.42
     hul
    0.41
     znaj
    0.41
    вёр
    0.41
    POSITIVE LOGITS
    감독
    0.51
    _{-
    0.51
    íns
    0.50
    rmann
    0.48
    rito
    0.45
    উদ্দিন
    0.45
    berts
    0.44
    ILIO
    0.44
    AZIONE
    0.44
    že
    0.43
    Activations Density 0.000%

    No Known Activations