© 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. 59116
    Prev
    Next
    INDEX
    Explanations

    until recently

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

    The neuron responds to longer tokens—that is, words with 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
    ांकि
    -1.41
     zunächst
    -1.21
    Dès
    -1.18
    (++
    -1.13
    ModelAdmin
    -1.05
    itic
    -0.99
    пс
    -0.96
     eerste
    -0.93
    :[{
    -0.93
    ències
    -0.92
    POSITIVE LOGITS
     recently
    9.75
     recent
    8.56
    Recently
    7.53
    recently
    7.22
     Recently
    7.13
    recent
    6.88
     недавно
    6.63
    Recent
    6.41
     recientemente
    6.38
     reciente
    6.06
    Activations Density 0.491%

    No Known Activations