© 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. 190172
    Prev
    Next
    INDEX
    Explanations

    ATM, CEO, parents, lens components

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

    SAP HCM text templates

    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
     แรง
    0.46
    drawable
    0.45
    katkan
    0.44
     radiographs
    0.43
     kur
    0.42
    gross
    0.42
     홈
    0.41
     Thiết
    0.41
    StateMachine
    0.41
     stillness
    0.41
    POSITIVE LOGITS
     incubated
    0.51
    虻
    0.51
    ك
    0.50
    ين
    0.48
     vendredi
    0.47
     conocidas
    0.46
     гуляць
    0.46
    ُول
    0.46
     cart
    0.46
     cultivated
    0.45
    Activations Density 0.000%

    No Known Activations