© 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. 73314
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    The neuron strongly activates on the “->” pointer‐dereference/member‐access operator in C/C++‐style code.

    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
     rozum
    -1.14
     woda
    -1.09
     Gebet
    -1.05
     osoba
    -1.04
    の詳細
    -1.02
    やう
    -1.02
    rews
    -0.99
     podob
    -0.98
    を読む
    -0.98
     Tropfen
    -0.97
    POSITIVE LOGITS
     cajones
    1.05
    PASO
    1.04
     المتحدة
    1.02
     litoral
    1.02
     castillo
    1.02
    察觉
    1.01
     adoles
    1.00
     bahia
    0.98
     drep
    0.97
     😘
    0.96
    Activations Density 0.003%

    No Known Activations