© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231192
    Prev
    Next
    INDEX
    Explanations

    school and academic titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Subst
    0.43
    矍
    0.41
    :
    0.41
     bens
    0.40
    вами
    0.40
    0.40
     Umfang
    0.39
    予防
    0.38
    差
    0.38
    ﭘ
    0.38
    POSITIVE LOGITS
     testify
    0.52
     frantically
    0.48
     영상을
    0.48
    ܡ
    0.47
     matemáticas
    0.47
     ন্যূনতম
    0.47
     outperform
    0.47
     Eğer
    0.47
     pomiędzy
    0.47
     수학
    0.46
    Activations Density 0.001%

    No Known Activations