© 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. 202914
    Prev
    Next
    INDEX
    Explanations

    skeptic

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

    start of descriptive phrases

    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
    우리
    0.51
    Д
    0.44
    ρν
    0.44
     severally
    0.44
    Б
    0.44
     PPG
    0.43
     Dang
    0.43
     Maire
    0.43
    А
    0.43
    କ
    0.43
    POSITIVE LOGITS
    leş
    0.47
    eless
    0.45
     كلمه
    0.45
    wort
    0.45
    esti
    0.43
    öst
    0.43
    读者
    0.43
     berlang
    0.43
    ei
    0.42
    ให้กับ
    0.42
    Activations Density 0.000%

    No Known Activations