© 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. 95737
    Prev
    Next
    INDEX
    Explanations

    vegetables

    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
    ta
    -1.34
    ейс
    -1.25
     rosario
    -1.23
    кономі
    -1.23
     patrick
    -1.22
    at
    -1.20
     castelo
    -1.20
     gustado
    -1.19
     engl
    -1.17
    "
    -1.17
    POSITIVE LOGITS
    alarme
    1.41
     \&
    1.36
     according
    1.32
    beyaz
    1.32
     پروفایل
    1.31
    嫌い
    1.30
    här
    1.30
     We
    1.30
     Our
    1.28
    utuhan
    1.25
    Activations Density 0.019%

    No Known Activations