© 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. 31-GEMMASCOPE-2-RES-65K
    7. 52331
    Prev
    Next
    INDEX
    Explanations

    object-oriented, objectification

    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_31_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
     be
    0.88
     ἐ
    0.73
     і
    0.72
     な
    0.71
    OP
    0.65
    aders
    0.65
     га
    0.63
     diluted
    0.63
     ін
    0.62
    {
    0.62
    POSITIVE LOGITS
     Object
    1.10
     object
    0.95
     objek
    0.95
     Objekt
    0.94
     Obj
    0.88
     OBJ
    0.86
     objs
    0.86
    t
    0.86
    object
    0.83
     Objects
    0.82
    Activations Density 0.079%

    No Known Activations