© 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. 104070
    Prev
    Next
    INDEX
    Explanations

    rabbi or code

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

    the word "Rabbi" (or related variants like "rabbi").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on occurrences of the identifier “textBox” (i.e. references to a UI textBox control variable).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    {
    -2.23
    of
    -2.20
    </h4>
    -2.17
     ſou
    -2.16
    BeginInit
    -2.16
     aktuelle
    -2.09
    /
    -2.02
     doigts
    -1.98
    being
    -1.95
    ю
    -1.95
    POSITIVE LOGITS
    𓆟
    2.42
     singola
    2.30
    𐄙
    2.27
    鬟
    2.22
     There
    2.13
    >
    2.11
     afectadas
    2.08
    釭
    2.08
     vanske
    2.06
     sabias
    2.06
    Activations Density 0.001%

    No Known Activations