Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41371
    Prev
    Next
    INDEX
    Explanations

    Sun followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    ny
    0.94
    ned
    0.86
    nings
    0.82
    ning
    0.80
    r
    0.78
    ný
    0.77
    nea
    0.76
    ners
    0.76
    nage
    0.76
    nin
    0.75
    POSITIVE LOGITS
     Night
    0.75
     daylight
    0.74
     night
    0.74
     Sun
    0.73
     nighttime
    0.65
    Night
    0.65
    釈
    0.64
     densely
    0.64
     precision
    0.64
     Jul
    0.64
    Activations Density 0.004%

    No Known Activations