© 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. 200286
    Prev
    Next
    INDEX
    Explanations

    as such, team discover, formal risk

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

    certain conditional outcomes

    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
    س
    0.51
    وک
    0.47
     impairments
    0.46
    됐
    0.45
    됬
    0.45
    etable
    0.44
    女生
    0.44
    י
    0.44
     khuẩn
    0.44
    ገለ
    0.44
    POSITIVE LOGITS
     Thunderbird
    0.50
     vele
    0.50
    zentration
    0.50
     technische
    0.47
    velope
    0.46
     folgenden
    0.46
     moet
    0.45
     muse
    0.45
     läng
    0.45
    ний
    0.44
    Activations Density 0.001%

    No Known Activations