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. 9073
    Prev
    Next
    INDEX
    Explanations

    check a

    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
    feeds
    0.45
    häuse
    0.45
    鶘
    0.44
    리를
    0.44
    鐢
    0.43
    ⍵
    0.43
    Externe
    0.42
    готовка
    0.41
    ències
    0.40
    ંકી
    0.40
    POSITIVE LOGITS
    т
    0.52
    ت
    0.52
    ut
    0.48
     movement
    0.46
     диа
    0.45
     meter
    0.44
    CHICAGO
    0.44
     ве
    0.44
     metre
    0.44
     kaleidoscopic
    0.43
    Activations Density 0.001%

    No Known Activations