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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12413
    Prev
    Next
    INDEX
    Explanations

    explaining terms and processes

    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_16k_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
    പ്ര
    0.47
    साम
    0.45
     شن
    0.44
    마다
    0.44
    ൪
    0.43
     perek
    0.42
     ghee
    0.42
     кирпи
    0.41
    তৃত
    0.41
    ずつ
    0.40
    POSITIVE LOGITS
    ja
    0.48
     successivo
    0.45
     ekonomik
    0.45
    枴
    0.44
     返回
    0.43
    洒落
    0.43
    éristiques
    0.42
     Moda
    0.42
     Lite
    0.42
    ιου
    0.42
    Activations Density 0.037%

    No Known Activations