© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 162223
    Prev
    Next
    INDEX
    Explanations

    benefits, location, amount, product

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

    concise explanations

    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
     установки
    0.50
     respecting
    0.49
     beneath
    0.48
     instalar
    0.47
    കൊ
    0.44
    瑩
    0.43
     underneath
    0.43
    MBA
    0.43
    zens
    0.43
     INSTALL
    0.42
    POSITIVE LOGITS
    㐰
    0.48
     twor
    0.47
    參数
    0.45
    Hepinize
    0.44
     தரு
    0.41
     linie
    0.40
    及ひ
    0.40
    इसे
    0.39
     hospice
    0.39
     biomedical
    0.39
    Activations Density 0.001%

    No Known Activations