© 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. 51152
    Prev
    Next
    INDEX
    Explanations

    whether or not

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

    Air Travel & Pilot's Dark Humor

    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
     peinture
    0.52
     causada
    0.50
     marques
    0.48
     causado
    0.48
     múlti
    0.47
     exécut
    0.46
     chevaux
    0.45
    庞
    0.45
     processo
    0.45
     katika
    0.45
    POSITIVE LOGITS
     తో
    0.55
    datal
    0.48
    aled
    0.47
    qrt
    0.47
    diameter
    0.46
    𝖙
    0.43
    assing
    0.42
    tol
    0.42
    cticamente
    0.42
    amins
    0.42
    Activations Density 0.000%

    No Known Activations