© 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. 22-GEMMASCOPE-RES-131K
    7. 67025
    Prev
    Next
    INDEX
    Explanations

    diamond geezer

    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
     staffel
    -1.16
     deko
    -1.09
     I
    -1.09
    _
    -1.09
    I
    -1.08
     poft
    -1.05
    G
    -1.01
     geladeira
    -1.00
     Katalog
    -0.98
    t
    -0.98
    POSITIVE LOGITS
     dones
    1.31
     músculo
    1.21
    ãng
    1.20
    Jenis
    1.19
     STARTED
    1.17
     DEFENDANT
    1.15
    ynchronously
    1.15
    瞜
    1.14
     cortar
    1.14
     ORDERED
    1.13
    Activations Density 0.003%

    No Known Activations