© 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. 25209
    Prev
    Next
    INDEX
    Explanations

    getters

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

    The neuron identifies occurrences of “get” method signatures or calls (i.e. the token “get” followed by parentheses).

    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
    
    -1.21
    なんか
    -1.15
    entrion
    -1.06
     BorderRadius
    -1.02
     WaitForSeconds
    -0.98
    UCIÓN
    -0.98
    ’
    -0.98
    Elaboración
    -0.97
     elsewhere
    -0.96
    lında
    -0.96
    POSITIVE LOGITS
     and
    1.16
     elettrico
    1.13
     perfettamente
    1.07
    のですか
    1.05
    のでしょう
    1.02
     comprendre
    1.00
     zgodnie
    1.00
     zamiast
    0.99
     mondi
    0.97
     gezondheid
    0.96
    Activations Density 0.002%

    No Known Activations