© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 111595
    Prev
    Next
    INDEX
    Explanations

    per, in, or rate measurements

    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
    大量
    0.44
    大量的
    0.41
    咏
    0.40
    鹘
    0.39
    ைகள்
    0.38
    FLICT
    0.38
     copious
    0.37
    勋
    0.37
     や
    0.36
    ოგ
    0.36
    POSITIVE LOGITS
     per
    0.71
     equivalent
    0.56
     Equivalent
    0.51
    per
    0.48
     equivalents
    0.48
     equivalente
    0.46
    equivalent
    0.46
     hydrochloride
    0.45
     प्रति
    0.44
    abor
    0.44
    Activations Density 0.034%

    No Known Activations