© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11298
    Prev
    Next
    INDEX
    Explanations

    collection and storage

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Dichlor
    -0.93
    xygen
    -0.90
     レザー
    -0.86
     Glaubens
    -0.86
    CultureInfo
    -0.85
     إليها
    -0.82
     alleen
    -0.82
     balles
    -0.82
    nergy
    -0.81
    Մ
    -0.81
    POSITIVE LOGITS
     collectors
    1.26
     collecting
    1.25
     collection
    1.13
    collecting
    1.13
     collector
    1.13
     collected
    1.13
    收集
    1.12
    Collected
    1.06
    收藏
    1.05
    Collecting
    1.05
    Activations Density 0.124%

    No Known Activations