© 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-262K
    7. 122952
    Prev
    Next
    INDEX
    Explanations

    cloud gaming support

    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_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
     ஆர்
    0.48
    澼
    0.48
    ుల
    0.47
     lije
    0.46
     Verantwort
    0.45
     வேறு
    0.45
     Ander
    0.45
    arım
    0.44
    вающая
    0.44
    蓁
    0.43
    POSITIVE LOGITS
    IN
    0.53
    IS
    0.53
    HE
    0.46
    mi
    0.45
    ino
    0.45
    ES
    0.44
    UT
    0.44
     insures
    0.43
    supports
    0.43
    Providing
    0.42
    Activations Density 0.002%

    No Known Activations