© 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. 22-GEMMASCOPE-RES-131K
    7. 54401
    Prev
    Next
    INDEX
    Explanations

    get read view method calls

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

    The neuron fires on common programming‐style verbs and keywords—especially function or method names like “func,” “get,” “read,” “list,” “view,” etc.

    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
     även
    -1.13
     additionally
    -0.94
     추가
    -0.91
    Ruj
    -0.90
    更に
    -0.87
     auch
    -0.86
     samtidigt
    -0.85
    Lepid
    -0.84
     encuentras
    -0.84
    ふわ
    -0.84
    POSITIVE LOGITS
    Everyone
    0.94
     who
    0.91
     bỏng
    0.90
    Who
    0.90
    нцип
    0.85
     Nachweis
    0.85
     Zufall
    0.84
    Until
    0.84
     plethora
    0.83
     Entwurf
    0.83
    Activations Density 0.007%

    No Known Activations