© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30162
    Prev
    Next
    INDEX
    Explanations

    math and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     più
    0.45
     თან
    0.42
     Antennes
    0.41
     Europeo
    0.40
     européens
    0.39
     PDFs
    0.39
    ディース
    0.38
    ᅵ
    0.38
    ３
    0.38
     Europeans
    0.38
    POSITIVE LOGITS
     Panama
    0.42
     menghadapi
    0.42
    靚
    0.41
    Karnataka
    0.41
    AJ
    0.40
     menampilkan
    0.39
     massage
    0.39
    Massage
    0.39
    asteroid
    0.39
     karena
    0.38
    Activations Density 0.002%

    No Known Activations