© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75214
    Prev
    Next
    INDEX
    Explanations

    Q: Preliminary studies

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

    The main thing this neuron does is detect the word “hacker.”

    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
    гают
    -1.12
     biografia
    -1.09
    FFECT
    -1.07
    рби
    -1.06
     emblema
    -1.03
     Funktionen
    -1.02
    etna
    -1.02
     Temporada
    -1.02
     plafon
    -1.02
    ίο
    -1.01
    POSITIVE LOGITS
     Since
    1.01
    or
    1.00
    Witam
    0.96
    지만
    0.95
     simple
    0.94
     القدس
    0.94
    برها
    0.94
    ၍
    0.93
    there
    0.93
    ಔ
    0.93
    Activations Density 0.000%

    No Known Activations