© 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. 34-GEMMASCOPE-RES-131K
    7. 115787
    Prev
    Next
    INDEX
    Explanations

    citations and journal names

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

    The neuron does not reliably activate on any tokens here and thus does not appear to detect a specific pattern.

    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
     burgeoning
    -1.13
    elesaikan
    -1.13
     Gemeinsame
    -1.12
     exquisitely
    -1.11
     meticulously
    -1.10
     ostensibly
    -1.09
     because
    -1.09
     unrelenting
    -1.08
     dazzling
    -1.06
     undoubtedly
    -1.05
    POSITIVE LOGITS
    atized
    1.34
     bardzo
    1.34
     a
    1.34
     prachtige
    1.27
     verschillende
    1.27
     abd
    1.26
     этому
    1.25
     anderen
    1.24
    𖧵
    1.23
    ècie
    1.18
    Activations Density 0.007%

    No Known Activations