© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79634
    Prev
    Next
    INDEX
    Explanations

    not [attribute]

    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
    ícias
    -1.24
    iamo
    -1.21
    킁
    -1.20
    uating
    -1.13
     soportes
    -1.13
    tocks
    -1.12
     zowel
    -1.11
     både
    -1.11
    それも
    -1.10
     ส์
    -1.10
    POSITIVE LOGITS
     as
    1.23
     but
    1.13
     like
    1.08
     over
    1.05
    corollary
    1.03
     Maybe
    1.03
     Perhaps
    1.02
    短信
    1.00
    内地
    0.99
     sophisticated
    0.96
    Activations Density 0.028%

    No Known Activations