© 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. 103941
    Prev
    Next
    INDEX
    Explanations

    YouTube – , custom cake toaster

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

    discomfort, drills, hope

    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
    ll
    0.51
    lg
    0.50
    ，
    0.50
    ͕
    0.49
    t
    0.48
     lr
    0.46
    骠
    0.46
     Block
    0.45
    x
    0.45
     k
    0.45
    POSITIVE LOGITS
    agt
    0.48
    áli
    0.46
     ခ
    0.44
     도시
    0.44
    urètre
    0.44
    ಿಗಳ
    0.44
     জেলা
    0.43
     bookArray
    0.43
    TimeString
    0.42
    udi
    0.42
    Activations Density 0.000%

    No Known Activations