© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 20651
    Prev
    Next
    INDEX
    Explanations

    fusion energy reactors

    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_16_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
     whereupon
    0.70
    ти
    0.68
    一
    0.68
    j
    0.65
     traum
    0.64
    ä
    0.64
    ném
    0.63
    и
    0.63
    之为
    0.61
    m
    0.60
    POSITIVE LOGITS
     Съ
    0.67
    quest
    0.64
    CT
    0.63
    ÃO
    0.61
    HTTPRequest
    0.61
    Concat
    0.60
    DIO
    0.60
     Sandwich
    0.59
     Polres
    0.59
     Highness
    0.59
    Activations Density 0.012%

    No Known Activations