© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2377
    Prev
    Next
    INDEX
    Explanations

    guilt, revenge, betrayal, loyalty

    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_16_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
    f
    0.77
    it
    0.71
    ing
    0.68
    is
    0.67
    ين
    0.66
    ol
    0.64
    u
    0.64
    ag
    0.63
    an
    0.62
    on
    0.61
    POSITIVE LOGITS
    ן
    0.54
     ד
    0.53
     ރ
    0.51
     Jealous
    0.48
     چ
    0.47
     venge
    0.47
     ล
    0.46
     vengeance
    0.46
     malicious
    0.46
     jealous
    0.46
    Activations Density 0.236%

    No Known Activations