© 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. 12-GEMMASCOPE-2-RES-65K
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    dig deep

    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_12_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
     (£
    1.21
    目が
    1.20
     of
    1.14
    目を
    1.14
    这篇文章
    1.13
     („
    1.11
     wasn
    1.09
     (
    1.08
    这家
    1.06
     (‘
    1.05
    POSITIVE LOGITS
     Saleh
    2.48
     plush
    2.40
    анд
    2.39
     чисто
    2.35
    aidl
    2.34
     tundra
    2.34
    функ
    2.34
    Diffuse
    2.31
    rinsic
    2.29
    дол
    2.26
    Activations Density 0.491%

    No Known Activations