© 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. 117623
    Prev
    Next
    INDEX
    Explanations

    replica set, All Rights

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

    The neuron flags unusually long tokens—i.e. words that span many characters.

    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
    tiga
    -0.68
     footnotes
    -0.65
    CACHE
    -0.63
     chaise
    -0.63
    graphique
    -0.62
    convex
    -0.61
    きち
    -0.61
     στιγ
    -0.60
    Puede
    -0.59
    resol
    -0.59
    POSITIVE LOGITS
     airways
    0.69
     brew
    0.68
     fry
    0.65
    ilov
    0.65
     potente
    0.65
    ншот
    0.65
    whitelist
    0.64
     Dadurch
    0.63
    atore
    0.62
     Dib
    0.62
    Activations Density 0.083%

    No Known Activations