© 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. 28461
    Prev
    Next
    INDEX
    Explanations

    citation numbers

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

    The neuron is essentially inactive and does not detect any particular pattern in the text.

    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
    好看的
    -1.16
    哧
    -1.10
     It
    -1.09
     the
    -1.09
    私の
    -1.09
     какой
    -1.07
    Namara
    -1.07
    を行いました
    -1.07
    を行います
    -1.07
     vorhandenen
    -1.05
    POSITIVE LOGITS
     with
    1.46
    Kā
    1.25
    Conseils
    1.20
    Cependant
    1.16
    Matériel
    1.16
    ennas
    1.13
    亟
    1.12
    ząd
    1.09
    Spéc
    1.05
    äldrar
    1.05
    Activations Density 0.002%

    No Known Activations