© 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. 69817
    Prev
    Next
    INDEX
    Explanations

    has/have a

    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
    "});
    1.26
    쩍
    1.21
    riage
    1.21
     المثل
    1.20
    きたい
    1.20
     justicia
    1.19
     ومرحبا
    1.18
    从此
    1.17
     отно
    1.16
     gini
    1.16
    POSITIVE LOGITS
     wafer
    1.77
     cultivated
    1.77
     injected
    1.73
     Bore
    1.72
     caster
    1.70
     shielded
    1.69
    拖
    1.67
    强大的
    1.66
     extended
    1.66
     grande
    1.64
    Activations Density 0.002%

    No Known Activations