© 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. 34-GEMMASCOPE-RES-131K
    7. 119015
    Prev
    Next
    INDEX
    Explanations

    depth and penetration

    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_34/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
     visitare
    -0.67
     CRP
    -0.65
     Findlay
    -0.63
    طار
    -0.63
    垢
    -0.63
     conoscere
    -0.62
    myList
    -0.62
    Learner
    -0.61
    診察
    -0.61
     โล
    -0.60
    POSITIVE LOGITS
     deep
    6.19
     deeper
    5.81
     depth
    5.81
    deep
    5.38
     deepest
    5.06
    depth
    5.03
    Depth
    4.69
     deepen
    4.66
    Deep
    4.66
     Depth
    4.63
    Activations Density 0.117%

    No Known Activations