© 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. 110
    Prev
    Next
    INDEX
    Explanations

    state of being or progression

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

    The neuron fires on words that signal escalation or development—comparative/superlative adjectives (fiercer, more diverse, than ever), progressive or result verbs (occurring, gaining, revealed, coming up, under construction), and similar markers of intensification or change.

    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
     when
    -2.41
     if
    -2.03
     because
    -1.94
     although
    -1.79
     but
    -1.75
     while
    -1.66
     should
    -1.64
     which
    -1.58
     that
    -1.57
     cuando
    -1.52
    POSITIVE LOGITS
    感じが
    1.31
    感じで
    1.28
    感じです
    1.20
    越來
    1.17
     coraz
    1.16
    こともあり
    1.15
    わけではない
    1.13
    zwischen
    1.13
     anonyme
    1.11
    mí
    1.10
    Activations Density 0.029%

    No Known Activations