© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39863
    Prev
    Next
    INDEX
    Explanations

    actions and statements

    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
     évé
    -1.13
     préoccup
    -1.09
    íti
    -1.01
    дизайн
    -1.00
    !」
    -1.00
     APPELL
    -0.99
     argentino
    -0.98
    ühner
    -0.98
     Kategor
    -0.97
    앗
    -0.97
    POSITIVE LOGITS
     colleagues
    1.07
     exigencias
    1.01
     entonces
    0.99
    を行いました
    0.98
    際には
    0.97
    を行います
    0.95
     fellow
    0.95
    のでしょう
    0.95
     others
    0.94
     acabamento
    0.94
    Activations Density 0.031%

    No Known Activations