© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101797
    Prev
    Next
    INDEX
    Explanations

    the topic or security

    np_acts-logits-general · gemini-2.5-flash-lite

    prepositions that introduce phrases or clauses, particularly "to," "by," "in," "on," and "that."

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alebo
    -1.76
     или
    -1.63
     restera
    -1.63
    ꜆
    -1.59
     adaptés
    -1.56
    蹑
    -1.56
    mø
    -1.53
     awaken
    -1.53
     atau
    -1.52
    chées
    -1.50
    POSITIVE LOGITS
    T
    1.75
    From
    1.75
    R
    1.66
    V
    1.62
     whatnot
    1.61
    </td>
    1.55
    旅程
    1.46
    As
    1.46
    那么
    1.45
    アド
    1.43
    Activations Density 0.263%

    No Known Activations