© 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. 7397
    Prev
    Next
    INDEX
    Explanations

    Daughters American Revolution Space Network

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

    DPU, DPIA, NIDA, DSL

    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
     rę
    0.46
     nicht
    0.42
     muy
    0.41
     hangi
    0.40
     Tugas
    0.40
     kesin
    0.39
     nada
    0.39
     태
    0.39
     meist
    0.39
     sog
    0.38
    POSITIVE LOGITS
    DSC
    0.53
    DX
    0.46
    DT
    0.43
    DCT
    0.43
    
    0.42
    Displayed
    0.42
    Dt
    0.41
     DSA
    0.41
    κ
    0.41
     DSC
    0.41
    Activations Density 0.160%

    No Known Activations