© 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. 75301
    Prev
    Next
    INDEX
    Explanations

    do not verbs

    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
    かもし
    -1.31
     materie
    -1.30
    ündete
    -1.27
     properly
    -1.23
    Setiap
    -1.20
    вобо
    -1.20
    愜
    -1.19
    توضیحات
    -1.18
    Masukkan
    -1.16
     autonomia
    -1.16
    POSITIVE LOGITS
    criminate
    1.30
    ,
    1.28
    低
    1.20
     meteen
    1.14
     "
    1.14
                    
    1.14
    "
    1.13
    J
    1.12
    A
    1.11
     इसे
    1.10
    Activations Density 0.022%

    No Known Activations