© 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. 23584
    Prev
    Next
    INDEX
    Explanations

    betrayal, compromise, or sell out

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

    making compromises

    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
    帙
    0.46
    ີ່
    0.43
    𒌉
    0.41
    溌
    0.41
     bumpers
    0.40
    ্মার
    0.40
     multifunction
    0.40
     витами
    0.40
    清新
    0.40
    霖
    0.40
    POSITIVE LOGITS
     acquies
    1.05
     betray
    1.00
     comprom
    0.94
     compromise
    0.93
     betrayed
    0.89
     betrayal
    0.88
     compromises
    0.88
     allegiance
    0.87
     compromised
    0.84
    comprom
    0.82
    Activations Density 0.140%

    No Known Activations