© 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. 123595
    Prev
    Next
    INDEX
    Explanations

    Gemini AI and ethical considerations

    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
    2
    0.47
    i
    0.47
    7
    0.45
    vi
    0.44
    лі
    0.43
    Doc
    0.43
    empirical
    0.43
    <0xBA>
    0.42
    voli
    0.42
    لي
    0.42
    POSITIVE LOGITS
     permeates
    0.48
     Challenges
    0.47
     allergens
    0.46
     emble
    0.46
     进入
    0.45
     penetrates
    0.44
     attendants
    0.43
     dashboards
    0.43
     conditioners
    0.43
     industriales
    0.43
    Activations Density 0.007%

    No Known Activations