© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 62
    Prev
    Next
    INDEX
    Explanations

    practical details

    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
     Arrows
    2.24
    囝
    2.13
    佢
    2.12
     entrambi
    2.11
    真是
    2.10
     adjournment
    2.02
     Which
    2.01
     Organisation
    1.99
     organisation
    1.98
    revision
    1.98
    POSITIVE LOGITS
     combust
    1.70
    7
    1.63
    ຖານ
    1.51
    8
    1.49
     obey
    1.49
    츠
    1.49
    req
    1.48
     react
    1.45
     emit
    1.41
     Hadid
    1.39
    Activations Density 0.552%

    No Known Activations