© 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. 110658
    Prev
    Next
    INDEX
    Explanations

    high definition

    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
    گیرد
    -0.74
    ねん
    -0.69
    怎样的
    -0.69
    はなく
    -0.68
     càng
    -0.65
     साथ
    -0.65
     llevaron
    -0.64
    ไลน์
    -0.63
     ánh
    -0.63
    銹
    -0.63
    POSITIVE LOGITS
     Definition
    3.73
    Definition
    3.53
     definition
    3.50
    definition
    3.28
     DEFINITION
    2.75
    DEFINITION
    2.73
     definitions
    2.61
     definición
    2.42
     Definitions
    2.31
     définition
    2.31
    Activations Density 0.074%

    No Known Activations