© 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. 35328
    Prev
    Next
    INDEX
    Explanations

    lists of specific items

    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
    ṁ
    -1.13
    operatives
    -1.13
     others
    -1.10
    oneof
    -1.03
     名
    -1.02
    者が
    -0.99
    пания
    -0.98
     one
    -0.96
    Five
    -0.96
     девушка
    -0.96
    POSITIVE LOGITS
     accompagné
    1.13
    iciens
    1.10
     помогают
    1.07
     tuturor
    1.07
     především
    1.07
    usky
    1.06
    verteilung
    1.05
    TGF
    1.05
     fortuner
    1.05
     "!
    1.05
    Activations Density 0.095%

    No Known Activations