© 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. 12496
    Prev
    Next
    INDEX
    Explanations

    to verb

    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
     ilustrasi
    -1.26
     different
    -1.25
     necesitaba
    -1.20
    ご理解
    -1.19
    ほら
    -1.18
     voordelen
    -1.16
     volverá
    -1.12
     crece
    -1.11
    青空
    -1.11
     verschillen
    -1.09
    POSITIVE LOGITS
     litoral
    1.21
    vaila
    1.15
    นาย
    1.13
     '*':
    1.10
     situe
    1.10
     väg
    1.09
    鉝
    1.09
    ปลา
    1.08
    nemia
    1.05
     TextAppearance
    1.05
    Activations Density 0.057%

    No Known Activations