© 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. 15923
    Prev
    Next
    INDEX
    Explanations

    explaining or describing text fragments

    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
     ಆಯ್
    0.47
     singleArray
    0.44
     usamos
    0.44
    esam
    0.43
     எனவே
    0.42
     نحاول
    0.42
     एनसीआरटी
    0.42
    🖉
    0.42
    ឬ
    0.42
    把它
    0.41
    POSITIVE LOGITS
     alongside
    0.47
     Alongside
    0.42
     aforementioned
    0.40
     revelations
    0.38
     hotspots
    0.38
     depictions
    0.38
    Alongside
    0.38
    ~(\
    0.37
     aristocratic
    0.37
     dungeons
    0.36
    Activations Density 0.013%

    No Known Activations