© 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. 71794
    Prev
    Next
    INDEX
    Explanations

    replace or substitute

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

    The neuron fires on isolated single‐character tokens (e.g. lone letters or punctuation marks).

    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
     aluminio
    -0.89
    erson
    -0.87
     lakini
    -0.85
    becoming
    -0.84
     vendredi
    -0.83
     revés
    -0.83
     Shetterly
    -0.82
    []=
    -0.82
     ralla
    -0.82
     haar
    -0.80
    POSITIVE LOGITS
     instead
    1.52
     вместо
    1.04
     because
    1.03
    Instead
    1.01
    代わりに
    1.00
     replace
    0.96
     Replace
    0.96
     benzer
    0.95
     sostitu
    0.94
    instead
    0.94
    Activations Density 0.072%

    No Known Activations