© 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. 32453
    Prev
    Next
    INDEX
    Explanations

    scandalous resignations and apologies

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

    reputation crisis and legal issues

    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
    ιουργ
    0.47
    stimulating
    0.46
     ጨ
    0.45
     увеличения
    0.45
    厙
    0.43
    薑
    0.42
     exciting
    0.42
     estimular
    0.42
     синх
    0.42
    冪
    0.41
    POSITIVE LOGITS
     crisis
    0.89
     apology
    0.85
     Crisis
    0.82
    道歉
    0.81
     disgraced
    0.80
    Crisis
    0.80
     scandal
    0.79
     apologized
    0.78
     crise
    0.77
    crisis
    0.76
    Activations Density 0.142%

    No Known Activations