© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7271
    Prev
    Next
    INDEX
    Explanations

    humiliation and scorn

    np_acts-logits-general · gemini-2.5-flash-lite

    negative judgment or disapproval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    0.47
    C
    0.46
     পরবর্তীতে
    0.41
    ALL
    0.41
    A
    0.40
    Overall
    0.39
    B
    0.39
    UC
    0.38
     ከፍተኛ
    0.38
    L
    0.38
    POSITIVE LOGITS
     अपमान
    0.51
     humiliated
    0.50
     meinem
    0.50
     despised
    0.50
     denunci
    0.49
     humiliation
    0.49
     humili
    0.49
     ненави
    0.48
     scorn
    0.47
     nación
    0.46
    Activations Density 0.018%

    No Known Activations