© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72726
    Prev
    Next
    INDEX
    Explanations

    figures, Twin Earths, Age

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

    The neuron fires on test‐double setup and verification calls—i.e. RSpec-style “allow(...).to receive(...)” or “expect(...).to receive(...)” constructs.

    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
    ální
    -1.00
     blaue
    -0.93
    menistan
    -0.91
    issent
    -0.90
    ----</
    -0.90
    papi
    -0.90
    ɫ
    -0.88
    ÚS
    -0.88
    ßig
    -0.88
    issez
    -0.88
    POSITIVE LOGITS
    <em>
    0.99
    帽子
    0.94
    pagna
    0.87
    /*
    0.83
     its
    0.82
    痊
    0.82
    <i>
    0.82
    Its
    0.79
     бывает
    0.78
    TryGetValue
    0.77
    Activations Density 0.007%

    No Known Activations