© 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. 61453
    Prev
    Next
    INDEX
    Explanations

    explaining or describing 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_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
    -------
    -1.53
     geprüft
    -1.40
     citazioni
    -1.34
    嚼
    -1.29
    :
    -1.28
    鯉
    -1.28
    たちも
    -1.27
    خبر
    -1.25
    >
    -1.25
    如果你
    -1.22
    POSITIVE LOGITS
     why
    1.48
    ௰
    1.34
     Publicar
    1.30
     iedereen
    1.30
     tevreden
    1.27
    锲
    1.26
     expresses
    1.25
    饧
    1.24
    以上です
    1.24
    ;;)
    1.24
    Activations Density 0.040%

    No Known Activations