© 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. 2804
    Prev
    Next
    INDEX
    Explanations

    names followed by related words

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

    Venetian Lagoon

    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
    朿
    0.57
    呠
    0.55
    쾺
    0.52
    InsertInt
    0.50
    煕
    0.50
    灿
    0.48
    枼
    0.47
    匽
    0.47
    陕
    0.46
    
    0.46
    POSITIVE LOGITS
    PEG
    1.61
    peg
    1.60
    Peg
    1.58
    hag
    1.55
     PEG
    1.55
     Hag
    1.48
     JAG
    1.48
     Chag
    1.48
    zag
    1.47
    zeg
    1.46
    Activations Density 0.400%

    No Known Activations