© 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. 228254
    Prev
    Next
    INDEX
    Explanations

    felon suicide criminal diplomat crime

    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
    ренных
    0.59
    ренные
    0.52
    Еще
    0.49
    珵
    0.49
    фан
    0.47
    கு
    0.46
    С
    0.46
    рых
    0.46
    드
    0.46
    Გ
    0.45
    POSITIVE LOGITS
     felon
    0.50
     suicide
    0.46
    yai
    0.46
    pe
    0.46
     sacrifices
    0.45
     sacrificial
    0.45
     अपराधी
    0.44
     نفرت
    0.44
     diplomat
    0.43
     crime
    0.43
    Activations Density 0.000%

    No Known Activations