© 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. 40036
    Prev
    Next
    INDEX
    Explanations

    no possibility, no difference, not have

    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
    liun
    -1.09
    最终
    -1.08
    别的
    -1.06
     juſ
    -1.05
    jeron
    -1.02
     âgées
    -1.01
     biela
    -1.00
     certaines
    -0.99
     accompagner
    -0.99
    really
    -0.98
    POSITIVE LOGITS
     such
    1.46
    同様
    1.39
     тако
    1.38
     такого
    1.38
     this
    1.24
     таких
    1.22
     ditto
    1.18
    同样的
    1.14
     такую
    1.12
    Similarly
    1.11
    Activations Density 0.074%

    No Known Activations