© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15679
    Prev
    Next
    INDEX
    Explanations

    urban density and location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ئۇ
    0.52
     Temperatura
    0.50
    涵盖
    0.49
    玦
    0.49
    妫
    0.48
    ixin
    0.47
     protokol
    0.47
    斛
    0.47
    运算符
    0.46
    装饰
    0.46
    POSITIVE LOGITS
     density
    0.90
     locations
    0.88
     cities
    0.86
     siting
    0.86
     clustering
    0.85
     neighbourhoods
    0.85
     villages
    0.84
     proximity
    0.82
     densities
    0.81
     location
    0.81
    Activations Density 0.064%

    No Known Activations