© 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. 4143
    Prev
    Next
    INDEX
    Explanations

    code context or considerations

    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
    7
    1.52
     unisex
    1.48
    8
    1.40
    寅
    1.38
     intermedi
    1.37
     mezzanine
    1.34
    uuuu
    1.33
     للنساء
    1.32
    資本
    1.31
    6
    1.30
    POSITIVE LOGITS
     today
    1.36
    '
    1.35
     historians
    1.34
     adjournment
    1.33
     venc
    1.32
    날
    1.32
     yesterday
    1.32
    ’
    1.32
    日的
    1.31
    浯
    1.29
    Activations Density 0.039%

    No Known Activations