© 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. 114338
    Prev
    Next
    INDEX
    Explanations

    dollars away

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

    riddle about father

    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
    уз
    0.50
    ంది
    0.47
    дов
    0.43
    :
    0.43
    的主要
    0.42
    ὺ
    0.42
    حت
    0.41
    ز
    0.41
    main
    0.40
    cstdlib
    0.40
    POSITIVE LOGITS
     mourn
    0.57
     നിന്നും
    0.51
     came
    0.49
     celebrates
    0.48
    วัสดี
    0.46
     booty
    0.46
     heartbroken
    0.46
     Bar
    0.46
    olik
    0.46
     sorrow
    0.45
    Activations Density 0.002%

    No Known Activations