© 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. 13120
    Prev
    Next
    INDEX
    Explanations

    available or Closed words

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

    The neuron is looking for “not available” statements—that is, phrases that indicate something is unavailable.

    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
     praticamente
    -1.16
    笵
    -1.16
     nguyen
    -1.13
     trattano
    -1.10
     verschillende
    -1.10
     エロ
    -1.09
    それも
    -1.08
    zeichneten
    -1.07
     掃除
    -1.07
    ggg
    -1.07
    POSITIVE LOGITS
     any
    1.84
     or
    1.65
     if
    1.62
     nor
    1.36
     other
    1.33
     aquellos
    1.29
     just
    1.27
     those
    1.22
     certain
    1.19
     under
    1.15
    Activations Density 0.031%

    No Known Activations