© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39815
    Prev
    Next
    INDEX
    Explanations

    biblical figures and fairy tales

    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_22/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
    mostly
    -1.38
    primarily
    -1.29
    perhaps
    -1.28
    mainly
    -1.25
     tervez
    -1.20
    probably
    -1.19
    ÑO
    -1.17
     sillä
    -1.16
     schrijven
    -1.11
    こんなに
    -1.10
    POSITIVE LOGITS
     saluran
    1.14
     ролях
    1.12
    iornamento
    1.11
    ᐈ
    1.09
     on
    1.08
    Zm
    1.07
     ждать
    1.05
     changed
    1.02
    荒
    1.01
     ask
    0.99
    Activations Density 0.015%

    No Known Activations