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. 6309
    Prev
    Next
    INDEX
    Explanations

    technical terms and examples

    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
    ują
    0.64
    ン
    0.63
    νου
    0.57
    concert
    0.55
    unz
    0.55
    un
    0.54
    accès
    0.53
     കൂടുതൽ
    0.53
    ción
    0.52
     esencia
    0.52
    POSITIVE LOGITS
     Shree
    0.50
    \
    0.49
     Y
    0.47
     X
    0.46
     Father
    0.42
     Harlan
    0.42
    امله
    0.42
     eBay
    0.42
    你
    0.42
    肚子
    0.42
    Activations Density 0.000%

    No Known Activations