© 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. 242729
    Prev
    Next
    INDEX
    Explanations

    children, kids, products, uk

    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
     pérd
    0.48
    𝐩
    0.46
    ക്കൂ
    0.45
    Holding
    0.44
    損失
    0.44
    繳
    0.44
    anything
    0.43
    꿀
    0.43
    他們
    0.43
    honest
    0.43
    POSITIVE LOGITS
     dilaksanakan
    0.43
     Remains
    0.43
    ervation
    0.42
     mengirim
    0.41
     sabah
    0.41
     remains
    0.41
     Sä
    0.41
     ternyata
    0.41
     (“
    0.41
     woke
    0.40
    Activations Density 0.000%

    No Known Activations