© 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. 31-GEMMASCOPE-2-RES-65K
    7. 40085
    Prev
    Next
    INDEX
    Explanations

    hotel requests

    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_31_width_65k_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
    耦
    0.45
     ट्रायंगल
    0.43
     fable
    0.43
     गोल
    0.42
     ჰ
    0.42
    URNIZOR
    0.41
     Й
    0.41
     глав
    0.40
     চাপ
    0.40
    OLYBD
    0.40
    POSITIVE LOGITS
    '
    0.51
    tex
    0.42
    ya
    0.41
    dev
    0.40
    anyi
    0.38
    ’
    0.38
     Micros
    0.38
    %;">
    0.36
    álogo
    0.36
    riad
    0.36
    Activations Density 0.002%

    No Known Activations