© 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. 51213
    Prev
    Next
    INDEX
    Explanations

    Kennedy and death

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

    specific terms or phrases

    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
    ή
    0.59
    த
    0.56
    νε
    0.54
    τά
    0.52
    ী
    0.50
    ધ
    0.49
    ר
    0.49
     Tears
    0.48
     lágrimas
    0.48
    ύ
    0.48
    POSITIVE LOGITS
    bitro
    0.46
     सरी
    0.41
    )).
    0.40
     waffle
    0.39
     dij
    0.38
    psis
    0.38
     genoeg
    0.38
    ])).
    0.38
     م
    0.38
     вообще
    0.37
    Activations Density 0.000%

    No Known Activations