© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64899
    Prev
    Next
    INDEX
    Explanations

    verified fan, college community, video submission, photo printers, investment management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    łoni
    -1.42
     parís
    -1.41
    為に
    -1.41
     nuov
    -1.38
     vegano
    -1.23
     adesivo
    -1.22
    ğın
    -1.20
     satria
    -1.20
     sincero
    -1.20
     preventivo
    -1.19
    POSITIVE LOGITS
    معرفی
    1.09
    这是什么
    1.08
    wać
    1.04
    zembro
    1.02
    velu
    1.01
    To
    1.01
     землю
    1.01
    zuje
    1.00
    If
    1.00
     متعلقه
    0.98
    Activations Density 0.281%

    No Known Activations