© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 49162
    Prev
    Next
    INDEX
    Explanations

    defining subjective terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_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
     ({
    0.42
     (%
    0.36
    []{
    0.35
     odpově
    0.35
    告诉
    0.34
    諳
    0.33
     odpowiedzi
    0.33
    ണ്ടു
    0.33
     décl
    0.33
     {...
    0.33
    POSITIVE LOGITS
    というのは
    0.57
     refers
    0.56
     implies
    0.53
     means
    0.53
     എന്നത്
    0.52
     అనేది
    0.52
     entails
    0.50
    とは
    0.50
    指的是
    0.48
     означает
    0.47
    Activations Density 0.050%

    No Known Activations