© 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. 34-GEMMASCOPE-RES-131K
    7. 107087
    Prev
    Next
    INDEX
    Explanations

    table descriptions and columns

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

    The neuron never activates (i.e. it’s effectively “dead” and doesn’t respond to any tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ostensibly
    -1.00
     getting
    -0.98
     by
    -0.98
    arlı
    -0.94
     disel
    -0.93
     trying
    -0.93
    八十
    -0.92
     because
    -0.92
     industria
    -0.91
     having
    -0.90
    POSITIVE LOGITS
    んでる
    0.99
    ctar
    0.98
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.98
     AMAZING
    0.96
    inyin
    0.96
     luscious
    0.95
     fünf
    0.94
    んだり
    0.93
     vijf
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    Activations Density 0.003%

    No Known Activations