© 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. 71327
    Prev
    Next
    INDEX
    Explanations

    connecting things

    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
    ☆☆☆☆☆
    -1.23
    Ḧ
    -1.20
    ♡♡
    -1.19
    🤭
    -1.19
     minuter
    -1.16
     recenti
    -1.15
    🏵
    -1.14
     eren
    -1.14
     vell
    -1.13
     €€
    -1.13
    POSITIVE LOGITS
     something
    1.46
     meant
    1.42
     we
    1.42
     resulted
    1.30
     result
    1.30
     still
    1.26
     worth
    1.20
     a
    1.16
     it
    1.13
     beantworten
    1.12
    Activations Density 0.045%

    No Known Activations