© 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. 36599
    Prev
    Next
    INDEX
    Explanations

    must read, see, hear, have, try

    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
     distintas
    -1.26
    常見
    -1.07
     externi
    -1.07
    してない
    -1.06
    这下
    -1.05
     encontramos
    -1.05
    comings
    -1.02
    そも
    -1.02
    她也
    -1.01
     troviamo
    -1.01
    POSITIVE LOGITS
     for
    2.06
     in
    1.57
     if
    1.34
    ทุก
    1.22
     unbedingt
    1.17
     Ordem
    1.17
     every
    1.16
    mıştır
    1.13
     обязательно
    1.12
     before
    1.11
    Activations Density 0.015%

    No Known Activations