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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15724
    Prev
    Next
    INDEX
    Explanations

    Jordan Brand, collectibles

    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
    BER
    0.38
     positive
    0.38
    positive
    0.38
    FR
    0.37
    crystall
    0.36
    men
    0.36
    re
    0.36
    ]=
    0.35
    ul
    0.35
    )=
    0.35
    POSITIVE LOGITS
     Shaq
    0.44
     tradición
    0.43
     când
    0.40
     Genealogy
    0.39
     Jordan
    0.39
     Nasıl
    0.38
     Cloudy
    0.38
     खरीद
    0.38
     Candy
    0.38
     Oscars
    0.37
    Activations Density 0.001%

    No Known Activations