Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 85135
    Prev
    Next
    INDEX
    Explanations

    highlighted phrases or concepts

    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
    Date
    0.45
     swell
    0.43
    ی
    0.43
    s
    0.41
     제시
    0.41
     dificult
    0.41
    Items
    0.40
    }$(
    0.40
    Od
    0.40
     pries
    0.39
    POSITIVE LOGITS
     HOMO
    0.51
     proactively
    0.46
     витами
    0.45
     injecting
    0.44
     +,
    0.44
     LeBron
    0.43
    াদিগের
    0.43
     trains
    0.43
    uity
    0.43
     ойнойт
    0.43
    Activations Density 0.008%

    No Known Activations