© 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. 10-GEMMASCOPE-RES-131K
    4. 659
    Prev
    Next
    INDEX
    Explanations

    navigation bar, controller, item

    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_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
     nocturna
    -1.55
    穽
    -1.45
    椟
    -1.45
    欷
    -1.44
    缡
    -1.44
    medlem
    -1.38
     família
    -1.37
    歘
    -1.34
    s
    -1.34
    əsi
    -1.34
    POSITIVE LOGITS
     You
    1.57
    haustible
    1.52
    を中心
    1.52
    ietic
    1.48
    の地
    1.38
     trofeo
    1.31
     Vous
    1.30
    會有
    1.27
    千万
    1.25
    iczne
    1.23
    Activations Density 0.040%

    No Known Activations