© 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. 228150
    Prev
    Next
    INDEX
    Explanations

    status, clothes, SCR

    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
    작가
    0.55
    意志
    0.48
    地区的
    0.47
    ెక్టర్
    0.47
    াফিক
    0.46
    တို့
    0.46
    姜
    0.46
    цени
    0.46
    服務
    0.46
    講師
    0.45
    POSITIVE LOGITS
     usp
    0.54
     on
    0.51
     ć
    0.49
    increased
    0.48
     zvý
    0.47
     outbursts
    0.46
    prac
    0.46
     allá
    0.46
    ż
    0.46
     ort
    0.46
    Activations Density 0.000%

    No Known Activations