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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4731
    Prev
    Next
    INDEX
    Explanations

    drink deep, premises based

    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
     adjournment
    1.38
    duit
    1.33
    囝
    1.28
     Thur
    1.25
    HOR
    1.24
    atted
    1.23
    :|
    1.23
     (’
    1.21
    highway
    1.20
     leaks
    1.17
    POSITIVE LOGITS
     usw
    2.76
    etc
    2.69
    6
    2.67
     Etc
    2.66
    此外
    2.48
    并且
    2.47
     инфра
    2.44
     etc
    2.44
    そして
    2.44
     وحتى
    2.42
    Activations Density 0.306%

    No Known Activations