© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40196
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    The neuron fires on capitalized identifiers denoting classes or types (e.g. LayoutInflater, NSWindow, Notification, Interceptor.Chain).

    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
     from
    -1.70
     like
    -1.34
    がて
    -1.33
     by
    -1.30
    為に
    -1.28
     for
    -1.27
    のお客様
    -1.25
    際に
    -1.23
     With
    -1.23
    性は
    -1.22
    POSITIVE LOGITS
    <bos>
    1.57
    などが
    1.39
    などを
    1.39
    などは
    1.36
    を
    1.30
    があります
    1.29
    つまり
    1.27
    そして
    1.27
    帮你
    1.26
    がありますが
    1.22
    Activations Density 0.004%

    No Known Activations