© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69827
    Prev
    Next
    INDEX
    Explanations

    time and its passage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     altogether
    1.96
    üşt
    1.81
     économ
    1.81
     quinze
    1.73
     réellement
    1.67
    }}{|
    1.67
     elective
    1.66
     laborales
    1.62
     healthiest
    1.62
     brink
    1.61
    POSITIVE LOGITS
    其
    1.12
    Ftp
    1.12
     παρου
    1.07
     obsah
    1.01
    zie
    1.01
    继承
    1.01
    πως
    1.00
    ə
    0.99
    оте
    0.99
     powod
    0.97
    Activations Density 0.001%

    No Known Activations