© 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. 1178
    Prev
    Next
    INDEX
    Explanations

    overall summary

    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
    hesda
    1.39
    isteria
    1.32
    (!$
    1.30
    ebabkan
    1.29
    stwa
    1.25
     #${
    1.23
    脷
    1.23
     stipulates
    1.20
    渍
    1.20
    枧
    1.20
    POSITIVE LOGITS
     Summary
    1.68
     overall
    1.68
     Overall
    1.61
     nutshell
    1.56
     More
    1.51
    Overall
    1.50
     Further
    1.50
    总结
    1.50
     summary
    1.49
    最终
    1.48
    Activations Density 0.091%

    No Known Activations