© 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. 1110
    Prev
    Next
    INDEX
    Explanations

    local services, places, and communities

    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
    "("
    1.99
     گاه
    1.99
    ة
    1.96
     Ceremony
    1.88
    wej
    1.85
    ڦ
    1.79
    ࿔
    1.79
    ළු
    1.78
     gönder
    1.75
    퐁
    1.72
    POSITIVE LOGITS
    province
    2.53
    北部
    2.49
     Northeast
    2.43
     province
    2.43
     counties
    2.42
     comté
    2.42
     County
    2.42
     borough
    2.41
    county
    2.39
     county
    2.37
    Activations Density 0.872%

    No Known Activations