© 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. 10-GEMMASCOPE-RES-131K
    7. 105185
    Prev
    Next
    INDEX
    Explanations

    concrete nouns and concepts

    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_10/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
     each
    -1.84
     their
    -1.60
     if
    -1.34
     theres
    -1.33
    }
    -1.23
     krijg
    -1.21
    继续
    -1.18
     consegui
    -1.18
    第一个
    -1.17
     borboleta
    -1.17
    POSITIVE LOGITS
     is
    1.58
    OnClickListener
    1.38
    daki
    1.37
    quelize
    1.36
    Ȯ
    1.35
    ")){
    1.33
    řejmě
    1.30
     anderer
    1.27
     FORD
    1.26
    場は
    1.25
    Activations Density 0.222%

    No Known Activations