© 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. 10988
    Prev
    Next
    INDEX
    Explanations

    generally or usually

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

    primarily, typically, majority

    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
     selfie
    0.43
     🥰
    0.43
     selfies
    0.43
     WeChat
    0.40
    داع
    0.40
    🥺
    0.40
     emojis
    0.40
    🤭
    0.39
     morphisms
    0.39
     komunikasi
    0.38
    POSITIVE LOGITS
     일반적으로
    0.51
     সাধারণত
    0.50
     대부분
    0.49
     досить
    0.49
     стандарт
    0.47
     oftentimes
    0.47
     பெரும்பாலும்
    0.46
     тради
    0.45
     பொதுவாக
    0.45
     протягом
    0.44
    Activations Density 0.178%

    No Known Activations