© 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. 25140
    Prev
    Next
    INDEX
    Explanations

    read more

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

    The neuron fires on numeric “read more” or “(more)” indicators—counts and continuation prompts that show how many items or characters are hidden behind a “read more” link.

    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
    ！！！！！
    -1.24
    quartered
    -1.20
     matematika
    -1.19
     gols
    -1.12
     anla
    -1.11
     legenda
    -1.11
    -1.11
     pneu
    -1.09
     taba
    -1.09
    thday
    -1.07
    POSITIVE LOGITS
    ↵↵↵↵↵
    1.07
     also
    1.00
    看到的
    0.99
     dře
    0.99
    toxicity
    0.99
     still
    0.94
    也可
    0.92
    more
    0.91
    ↵↵↵↵↵↵↵
    0.89
     composición
    0.88
    Activations Density 0.017%

    No Known Activations