© 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. 2501
    Prev
    Next
    INDEX
    Explanations

    prefixes for locations

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

    The Trevor Project

    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
     Questi
    0.24
     Regex
    0.22
     xhrObj
    0.21
     Electrons
    0.21
     adduct
    0.21
     Ignore
    0.21
     manually
    0.21
     各
    0.21
     politely
    0.21
     نے
    0.20
    POSITIVE LOGITS
     Philadelphia
    0.26
     Somerset
    0.23
     Dublin
    0.22
     Pittsburgh
    0.22
     Norwich
    0.21
    Philadelphia
    0.21
     Melbourne
    0.21
     Sarasota
    0.21
     Baltimore
    0.21
     Norfolk
    0.21
    Activations Density 0.482%

    No Known Activations