© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72630
    Prev
    Next
    INDEX
    Explanations

    to with

    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
    ‥
    -1.24
    もともと
    -1.10
    Spesifikasi
    -1.08
     selera
    -1.07
    dehyde
    -1.07
    ？？？
    -1.03
    Ār
    -1.02
    يًا
    -0.99
    IZATION
    -0.98
    大约
    -0.98
    POSITIVE LOGITS
     to
    1.39
     of
    1.27
     a
    1.20
    seag
    1.13
    perry
    1.11
    ayn
    1.07
     called
    1.05
    jango
    1.05
    dubai
    0.98
    atrici
    0.97
    Activations Density 0.025%

    No Known Activations