© 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. 200
    Prev
    Next
    INDEX
    Explanations

    different conditions

    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
     бампер
    -1.78
    ־ה
    -1.50
    וּ
    -1.47
     "}";
    -1.41
    ֶּ
    -1.34
     меда
    -1.30
     ложка
    -1.27
     pijn
    -1.25
    ̳
    -1.19
     Utf
    -1.17
    POSITIVE LOGITS
     different
    1.63
     not
    1.58
     nemico
    1.41
    摂取
    1.35
     kinds
    1.30
     stronger
    1.28
     when
    1.26
     Different
    1.25
     asesinato
    1.24
     різних
    1.20
    Activations Density 0.048%

    No Known Activations