© 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. 30451
    Prev
    Next
    INDEX
    Explanations

    teleport, flying, activatING

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

    The neuron activates broadly on ordinary content words (nouns, verbs, adjectives, pronouns) rather than on punctuation, formatting markers, or stop‐words.

    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
    äumt
    -0.88
     entrevist
    -0.88
    زیک
    -0.82
    ordinating
    -0.82
    composición
    -0.82
     周年
    -0.80
    //};
    -0.79
    connects
    -0.79
    แก้
    -0.79
    ումներ
    -0.78
    POSITIVE LOGITS
     levit
    1.77
     tele
    1.55
     use
    1.46
     teleport
    1.43
     using
    1.41
     activate
    1.36
    使用
    1.35
     uses
    1.28
     activates
    1.26
     casting
    1.23
    Activations Density 0.013%

    No Known Activations