© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12295
    Prev
    Next
    INDEX
    Explanations

    obsessive-compulsive, insipidus, anhydrases, consolidating

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

    scientific and technical terms, particularly in medical, chemical, and engineering contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     in
    -1.60
     from
    -1.32
    izado
    -1.24
     at
    -1.18
     on
    -1.17
     Mó
    -1.16
     comité
    -1.15
     tē
    -1.14
    њу
    -1.13
     vicente
    -1.13
    POSITIVE LOGITS
    を行い
    1.41
    為に
    1.26
    必要がある
    1.20
    沢山
    1.18
    どれだけ
    1.13
    ようです
    1.13
     rác
    1.11
    何回
    1.07
     breathtaking
    1.05
    if
    1.05
    Activations Density 0.484%

    No Known Activations