© 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. 36102
    Prev
    Next
    INDEX
    Explanations

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron doesn’t respond to any tokens—it remains inactive and thus isn’t detecting any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     groet
    -1.76
    ⽌
    -1.63
     vulgaires
    -1.49
     OGSÅ
    -1.48
     będ
    -1.47
    зраст
    -1.47
    nextProps
    -1.46
    Also
    -1.45
    鏽
    -1.45
     magasiner
    -1.44
    POSITIVE LOGITS
     
    1.62
     and
    1.51
     принял
    1.50
    Irlande
    1.47
    <bos>
    1.45
    上で
    1.39
    最重要的
    1.39
    などは
    1.36
     across
    1.35
     ответил
    1.35
    Activations Density 0.001%

    No Known Activations