© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2700
    Prev
    Next
    INDEX
    Explanations

    routes and journeys

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

    movement and flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뽑
    0.45
     implementar
    0.45
    に応
    0.42
     뽑
    0.42
     సహాయ
    0.41
    ायत
    0.40
     rispond
    0.40
    تقديم
    0.40
     உதவு
    0.40
    劝
    0.40
    POSITIVE LOGITS
     traversing
    1.88
     traverses
    1.84
     traverse
    1.80
     traversed
    1.65
     travels
    1.55
    traverse
    1.52
     travers
    1.49
     traveling
    1.48
     crossing
    1.47
     attravers
    1.46
    Activations Density 0.348%

    No Known Activations