© 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. 32683
    Prev
    Next
    INDEX
    Explanations

    biological or chemical components

    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
    ú
    0.63
     perdió
    0.50
    ū
    0.50
    érique
    0.49
    ículo
    0.47
     entreg
    0.47
    она
    0.47
    у
    0.46
     veulent
    0.46
    ún
    0.45
    POSITIVE LOGITS
     arrangements
    0.59
     Warranty
    0.50
     pigmentation
    0.50
     ribs
    0.49
     agreements
    0.48
     adaptability
    0.48
     sails
    0.48
     accommodations
    0.48
     protrusions
    0.48
     sores
    0.48
    Activations Density 0.002%

    No Known Activations