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. 6325
    Prev
    Next
    INDEX
    Explanations

    Specific titles and 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
    Nä
    0.27
    можно
    0.26
    ツ
    0.26
    ين
    0.26
    Rajas
    0.26
    ्रेट
    0.26
    のだ
    0.26
    い
    0.25
    ฟ
    0.25
    ۸
    0.25
    POSITIVE LOGITS
    -
    0.27
    utation
    0.26
     Photo
    0.25
     Rescue
    0.25
     Skate
    0.25
     brainchild
    0.25
    ’
    0.24
    ville
    0.23
     Community
    0.23
     revolution
    0.23
    Activations Density 0.814%

    No Known Activations