© 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. 14087
    Prev
    Next
    INDEX
    Explanations

    code and mathematical expressions

    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
     веществ
    -0.84
    結構
    -0.82
    So
    -0.81
     HomeComponent
    -0.79
    Also
    -0.76
    服装
    -0.75
    tamen
    -0.75
    memcmp
    -0.75
    子が
    -0.74
    They
    -0.74
    POSITIVE LOGITS
    vere
    0.88
     Enciclopedia
    0.84
    郿
    0.83
     zyn
    0.82
     leek
    0.81
    ᑎ
    0.81
    зії
    0.79
    personalized
    0.79
    Detta
    0.79
    附
    0.78
    Activations Density 0.028%

    No Known Activations