© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66114
    Prev
    Next
    INDEX
    Explanations

    get method calls

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

    The neuron responds to code tokens invoking “get…” methods (i.e. getter or accessor calls).

    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
    ᾽
    -1.15
     using
    -1.11
    Demografia
    -1.02
     there
    -1.01
     possibly
    -1.00
     their
    -0.98
     theoretically
    -0.97
     another
    -0.97
    分かります
    -0.95
     where
    -0.95
    POSITIVE LOGITS
    "].
    1.10
    estanding
    1.05
     борьбе
    1.04
    Ṣ
    1.02
    phoned
    1.02
    呜
    1.01
    emons
    0.98
    
    0.98
    стор
    0.97
     Receiving
    0.97
    Activations Density 0.003%

    No Known Activations