© 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. 132279
    Prev
    Next
    INDEX
    Explanations

    transatlantic flight

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

    transaction log & young girls

    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
    脯
    0.50
     rejoicing
    0.47
    繋がりたい
    0.46
    noodles
    0.46
    avgsalary
    0.46
     desperately
    0.45
     cultivos
    0.45
    🌯
    0.45
    प्ति
    0.45
     Aí
    0.45
    POSITIVE LOGITS
    zen
    0.53
     সড়
    0.52
    S
    0.50
    ed
    0.49
    VR
    0.47
    New
    0.47
    ע
    0.47
    Y
    0.46
    U
    0.46
    KEN
    0.46
    Activations Density 0.001%

    No Known Activations