© 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. 10-GEMMASCOPE-RES-131K
    7. 48212
    Prev
    Next
    INDEX
    Explanations

    expressing interest or concern

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

    The neuron fires on very short, common “function” tokens—little words (pronouns, prepositions) or single-character symbols (like dashes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     yesterday
    -1.73
     fufficient
    -1.49
     fometimes
    -1.48
     Meksi
    -1.46
    ÁND
    -1.45
    før
    -1.45
     entusi
    -1.43
     mosso
    -1.40
     gracios
    -1.38
    喼
    -1.38
    POSITIVE LOGITS
    <td>
    2.00
        
    1.82
    f
    1.81
    p
    1.65
    c
    1.64
     "
    1.53
     всех
    1.52
    %
    1.51
    ".
    1.48
    x
    1.48
    Activations Density 0.132%

    No Known Activations