© 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. 66621
    Prev
    Next
    INDEX
    Explanations

    itsits operating its

    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
     ragazza
    -1.40
     hábit
    -1.27
     splet
    -1.23
    ׇ
    -1.22
    ֺ
    -1.20
    Odpowiedz
    -1.17
    、【
    -1.16
     možnost
    -1.15
     someone
    -1.14
     bosques
    -1.13
    POSITIVE LOGITS
     operating
    1.76
    וּ
    1.69
     its
    1.55
    ּוֹ
    1.47
     OPERATING
    1.36
     السوق
    1.34
     itself
    1.28
     regulatory
    1.23
    וֹ
    1.22
     operate
    1.21
    Activations Density 0.040%

    No Known Activations