© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28968
    Prev
    Next
    INDEX
    Explanations

    set number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     highlighted
    0.52
     highlighter
    0.42
     발
    0.41
    高
    0.40
    validation
    0.40
     высо
    0.40
     underlined
    0.40
    發
    0.39
    highlight
    0.39
     detected
    0.39
    POSITIVE LOGITS
     числе
    0.42
     dang
    0.39
    万円
    0.38
     numérica
    0.38
    ड्डा
    0.38
    irp
    0.37
    CCc
    0.37
    ীষ
    0.37
    Countdown
    0.37
     RTR
    0.37
    Activations Density 0.000%

    No Known Activations