© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152999
    Prev
    Next
    INDEX
    Explanations

    have one side

    np_acts-logits-general · gemini-2.5-flash-lite

    keep parts

    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
    Negative Logits
    בח
    0.57
    Como
    0.55
    לא
    0.54
    בש
    0.51
    נ
    0.51
    Dalam
    0.49
    ברי
    0.49
    Plenty
    0.49
    Otros
    0.48
    ग्विजय
    0.48
    POSITIVE LOGITS
    :
    0.55
     movie
    0.54
    oo
    0.50
     audio
    0.50
     "
    0.50
     chili
    0.50
     oc
    0.49
    ron
    0.49
     contingency
    0.49
     det
    0.47
    Activations Density 0.001%

    No Known Activations