© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38577
    Prev
    Next
    INDEX
    Explanations

    line number context

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

    The neuron is essentially dead—it never activates and thus isn’t detecting any 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
    ㄤ
    -0.98
    lograph
    -0.96
    стюм
    -0.95
     xxii
    -0.89
     '-
    -0.88
     Также
    -0.88
     jp
    -0.88
    chowy
    -0.86
    였
    -0.84
    蝙
    -0.84
    POSITIVE LOGITS
     here
    1.29
     no
    1.08
     one
    0.85
     Donde
    0.84
     where
    0.83
    Título
    0.82
     сюда
    0.82
    rededor
    0.81
     pozdě
    0.81
    的一個
    0.80
    Activations Density 0.001%

    No Known Activations