© 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. 177237
    Prev
    Next
    INDEX
    Explanations

    continue to provide

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

    family, antagonist, forest, company

    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
     அந்
    0.52
     mêmes
    0.52
     الا
    0.47
     दिव्यांग
    0.46
     얼마나
    0.46
     해당
    0.46
    該
    0.45
     வன
    0.44
     άλλα
    0.44
     sejam
    0.44
    POSITIVE LOGITS
    w
    0.54
    bereich
    0.45
     here
    0.45
     sev
    0.44
    ଶ
    0.44
    Sev
    0.43
    Op
    0.43
    oport
    0.43
     photoelectron
    0.43
    neath
    0.42
    Activations Density 0.001%

    No Known Activations