© 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. 27558
    Prev
    Next
    INDEX
    Explanations

    teenager or Indiana

    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
     "-",
    -1.23
     then
    -1.22
     シーン
    -1.17
     včetně
    -1.13
     other
    -1.11
     xvii
    -1.07
     augusti
    -1.05
    当時は
    -1.04
     others
    -1.03
     саны
    -1.03
    POSITIVE LOGITS
    ＾＾；
    1.17
    것은
    1.06
    　↓
    1.05
    Več
    1.05
    morgan
    1.05
    でご
    1.02
    －－
    1.00
    大丈夫
    1.00
    の通り
    0.99
    Lihat
    0.98
    Activations Density 0.079%

    No Known Activations