© 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. 12682
    Prev
    Next
    INDEX
    Explanations

    simplifies building, enables connections

    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
    tennis
    0.45
     whiche
    0.44
     Wolver
    0.44
    ensioni
    0.43
    牷
    0.42
     ppw
    0.42
    િવસે
    0.41
     تقریبا
    0.41
    this
    0.41
    мії
    0.41
    POSITIVE LOGITS
     t
    0.50
    Photos
    0.50
     stations
    0.49
     task
    0.47
     station
    0.45
     modality
    0.43
    Photo
    0.43
     kas
    0.43
     tight
    0.42
    Dropbox
    0.42
    Activations Density 0.000%

    No Known Activations