© 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. 246940
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their descriptors

    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
     sensitivity
    0.55
    N
    0.53
     entities
    0.52
    Sensitivity
    0.52
    Label
    0.51
     amu
    0.51
     ait
    0.49
     persons
    0.48
     exposure
    0.48
     reun
    0.48
    POSITIVE LOGITS
    ውን
    0.53
    corsi
    0.52
    ctype
    0.49
     Ihrem
    0.49
     Erfol
    0.48
     Determines
    0.47
     ;\
    0.47
     Lösung
    0.46
    gboost
    0.46
     Func
    0.46
    Activations Density 0.000%

    No Known Activations