© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 220339
    Prev
    Next
    INDEX
    Explanations

    collection of data or options

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

    spanking, kids cough, instant dry, expectation

    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
     PROBLE
    0.43
    ση
    0.43
    igu
    0.42
    ţional
    0.42
    idla
    0.41
     EDUCATION
    0.41
     Sq
    0.41
    b
    0.41
    sti
    0.40
    amn
    0.40
    POSITIVE LOGITS
    ाइज
    0.51
    FromNib
    0.49
    あるいは
    0.48
     किंवा
    0.46
    យើង
    0.43
     veya
    0.43
    ನ
    0.43
     muestras
    0.43
     yoki
    0.42
     staffers
    0.42
    Activations Density 0.001%

    No Known Activations