© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64480
    Prev
    Next
    INDEX
    Explanations

    without effects

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

    The neuron flags highly informative, topic‐specific content words (salient nouns and adjectives) that capture the main subject or key theme of a passage.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     newVal
    -0.84
    Kesimpulan
    -0.84
    esor
    -0.83
    🔂
    -0.79
     verlassen
    -0.78
    郝
    -0.78
     求
    -0.76
    ленно
    -0.75
     judgment
    -0.75
     Refuge
    -0.74
    POSITIVE LOGITS
     without
    1.84
     safely
    1.74
     بدون
    1.65
     tanpa
    1.63
    without
    1.62
     but
    1.62
     ohne
    1.51
     WITHOUT
    1.39
     safe
    1.38
    ohne
    1.38
    Activations Density 0.159%

    No Known Activations