© 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. 31-GEMMASCOPE-2-RES-65K
    7. 9547
    Prev
    Next
    INDEX
    Explanations

    exile and confinement

    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
    開
    0.45
    いつも
    0.43
    िना
    0.43
    Cached
    0.41
    вого
    0.40
    Ри
    0.39
    GLOBAL
    0.38
    цы
    0.38
    Rec
    0.38
    开
    0.38
    POSITIVE LOGITS
     confining
    0.59
     humiliation
    0.56
     confinement
    0.55
     confines
    0.54
     servitude
    0.54
     humility
    0.50
     stint
    0.49
     obscurity
    0.49
     exile
    0.48
    豢
    0.47
    Activations Density 0.119%

    No Known Activations