© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    do

    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
     速
    2.89
     Vee
    2.82
     Entries
    2.63
     Css
    2.50
     organisers
    2.49
     Severn
    2.46
     historians
    2.40
     Arrows
    2.38
    dated
    2.36
     Revue
    2.35
    POSITIVE LOGITS
    rinsic
    3.23
    7
    3.15
    6
    2.94
    8
    2.87
    4
    2.63
    5
    2.59
    3
    2.53
    лежа
    2.42
     untuk
    2.38
     fizik
    2.38
    Activations Density 1.212%

    No Known Activations