© 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. 129383
    Prev
    Next
    INDEX
    Explanations

    literary fiction

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

    social and technical concepts

    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
     ภาพ
    0.50
     առաջ
    0.48
     บท
    0.45
    熠
    0.45
     อังกฤษ
    0.45
    GPa
    0.45
     ಅವರ
    0.44
     そこ
    0.44
    pots
    0.44
    𝗨
    0.43
    POSITIVE LOGITS
    imento
    0.49
    ποιη
    0.49
     ممكن
    0.48
    ката
    0.46
     she
    0.46
    زند
    0.46
     voorzien
    0.45
     conden
    0.45
     vielf
    0.44
     da
    0.43
    Activations Density 0.001%

    No Known Activations