© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36476
    Prev
    Next
    INDEX
    Explanations

    cynical amoral detachment

    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_40_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
     humbly
    0.47
     تربيع
    0.44
    aderos
    0.44
    哞
    0.44
     Audiodateien
    0.43
    stranded
    0.41
    វត្ត
    0.41
     strugg
    0.40
     stranded
    0.40
     inalámb
    0.40
    POSITIVE LOGITS
     ruthless
    1.29
     callous
    1.25
     cynical
    1.18
     ruth
    1.14
     cynicism
    1.13
     sadistic
    1.09
    😈
    1.09
     নিষ্ঠুর
    1.02
     cyn
    1.01
     coldly
    0.97
    Activations Density 0.019%

    No Known Activations