© 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-262K
    7. 128547
    Prev
    Next
    INDEX
    Explanations

    social conditioning

    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_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
    績
    0.45
    stieg
    0.43
     erweit
    0.43
     steig
    0.42
    軽
    0.42
     sast
    0.42
    lerden
    0.42
    oder
    0.41
     protagon
    0.41
     kesempatan
    0.40
    POSITIVE LOGITS
    ߋ
    0.44
     предназна
    0.43
     [(
    0.42
     unconditionally
    0.42
     destinée
    0.42
     destinés
    0.41
    antial
    0.40
     sued
    0.40
     marketed
    0.40
     fraudulently
    0.39
    Activations Density 0.008%

    No Known Activations