© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14441
    Prev
    Next
    INDEX
    Explanations

    social groups and members

    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_40_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
    nc
    0.50
    lal
    0.49
    lx
    0.45
    essere
    0.43
    sser
    0.43
    lado
    0.42
     Belong
    0.42
    l
    0.41
    ne
    0.41
    gar
    0.41
    POSITIVE LOGITS
     members
    1.02
     consisting
    0.93
     comprised
    0.91
     membros
    0.91
    成員
    0.87
     gồm
    0.87
    members
    0.84
    成员
    0.84
     composed
    0.83
     সদস্যরা
    0.80
    Activations Density 0.041%

    No Known Activations