© 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. 128015
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of the word “aim” (including its inflected forms like “aiming” or “aim at”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    indicating a goal or intention

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ဴ
    -2.61
    と思いますが
    -2.56
     wholly
    -2.52
    瑧
    -2.50
     Eigentümer
    -2.45
     encompassing
    -2.42
     overtly
    -2.36
    ’，
    -2.34
    あります
    -2.30
    vantaged
    -2.27
    POSITIVE LOGITS
    h
    3.06
    y
    3.00
            
    2.59
    s
    2.50
    </strong>
    2.38
     interessant
    2.31
     stelle
    2.30
     новые
    2.23
    tes
    2.20
    probably
    2.19
    Activations Density 0.025%

    No Known Activations