© 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. 1557
    Prev
    Next
    INDEX
    Explanations

    sustained energy, essential to, thus large

    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
     построен
    0.89
     المرا
    0.87
    」（
    0.79
     Cracked
    0.77
     construido
    0.77
     dissected
    0.75
    تق
    0.75
     (
    0.75
     broken
    0.74
     Shat
    0.74
    POSITIVE LOGITS
    ัตว์
    1.19
     conviv
    1.17
    ergic
    1.16
     jobId
    1.15
     idP
    1.15
     sinon
    1.14
    των
    1.14
     nere
    1.13
    autant
    1.12
     yě
    1.12
    Activations Density 0.035%

    No Known Activations