© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 621
    Prev
    Next
    INDEX
    Explanations

    dates and ordinals

    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_22_width_16k_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
     confound
    0.66
     уравнение
    0.66
     virtud
    0.65
     deriving
    0.65
     чуть
    0.62
     ഘ
    0.62
     uniqueness
    0.60
    derive
    0.60
    琇
    0.60
    iding
    0.60
    POSITIVE LOGITS
    th
    1.46
    ths
    1.06
     ቀን
    1.02
    日
    1.02
    일에
    0.95
     ရက်
    0.94
     তারিখে
    0.93
    న
    0.93
    nd
    0.93
    日記
    0.92
    Activations Density 0.384%

    No Known Activations