© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36002
    Prev
    Next
    INDEX
    Explanations

    combining into a cohesive description

    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
    insect
    0.45
     различных
    0.44
    discussion
    0.44
     exerts
    0.44
    pesar
    0.44
    تباين
    0.43
     estuvo
    0.42
    軖
    0.42
     noticia
    0.41
    стки
    0.41
    POSITIVE LOGITS
     बढ़ाकर
    0.46
     previously
    0.44
     Substance
    0.43
     komunitas
    0.43
     Gemeinschaft
    0.42
    ເລ
    0.41
     Qu
    0.41
     TensorFlow
    0.40
     exponential
    0.40
    Algebra
    0.40
    Activations Density 0.011%

    No Known Activations