© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 985
    Prev
    Next
    INDEX
    Explanations

    country tourism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     ause
    1.83
     επέ
    1.78
    뇰
    1.75
    }--
    1.71
     perform
    1.69
     inequ
    1.68
     osim
    1.65
     castom
    1.65
     effiz
    1.61
    @{
    1.60
    POSITIVE LOGITS
    ፕሮ
    2.21
    ľa
    2.00
     Adi
    2.00
    лят
    1.99
     Congo
    1.99
    明け
    1.98
    ｶ
    1.95
    nosť
    1.94
    ções
    1.94
    ଯ
    1.92
    Activations Density 0.520%

    No Known Activations