© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15079
    Prev
    Next
    INDEX
    Explanations

    street names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    formen
    0.56
    wirken
    0.53
     MBE
    0.52
     رہی
    0.51
     Rollins
    0.51
    CPS
    0.51
     কোম্প
    0.51
    偶
    0.51
    MPS
    0.50
    checker
    0.49
    POSITIVE LOGITS
     улица
    1.49
     rue
    1.48
     вули
    1.43
     Rue
    1.40
    ถนน
    1.38
     ถนน
    1.36
     улице
    1.34
     avenida
    1.32
    Rue
    1.32
     Jalan
    1.31
    Activations Density 0.036%

    No Known Activations