© 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. 2223
    Prev
    Next
    INDEX
    Explanations

    betrayal and hatred

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

    emotional distress and isolation

    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
     inkjet
    0.40
     தொழில்நுட்ப
    0.39
    掲載
    0.38
     ®
    0.38
     পুস্তক
    0.38
     perennial
    0.37
     опубликован
    0.37
    網友
    0.37
    ®
    0.36
    infrared
    0.36
    POSITIVE LOGITS
     betrayed
    0.59
     betrayal
    0.56
     traitor
    0.56
     betray
    0.54
     exiled
    0.48
     selfishness
    0.47
     قتل
    0.46
     cowardly
    0.46
     blackmail
    0.45
     hatred
    0.45
    Activations Density 0.317%

    No Known Activations