© 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. 51641
    Prev
    Next
    INDEX
    Explanations

    German singer

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

    describing scenes or actions

    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
    archy
    0.51
     ঊর্ধ্বতন
    0.51
    Moles
    0.45
    Fonts
    0.44
    дом
    0.44
    ilem
    0.43
    셔
    0.43
    innie
    0.42
    कंपनी
    0.42
    Company
    0.42
    POSITIVE LOGITS
     Lij
    0.51
     Hyp
    0.49
     这
    0.47
     Of
    0.46
    ၂
    0.46
     הת
    0.46
     Bitt
    0.46
     Hab
    0.46
     Regression
    0.46
     of
    0.45
    Activations Density 0.000%

    No Known Activations