© 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. 33186
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and semicolons

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

    The neuron activates on cleanup or teardown calls—methods that release or remove resources (e.g. `.close()`, `os.remove()`, `rmtree`, resource disposal).

    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
     инструк
    -0.89
    chauen
    -0.78
    itemBuilder
    -0.77
    uolo
    -0.77
     бумаги
    -0.77
     позволит
    -0.77
    ның
    -0.76
    ade
    -0.75
    setTransform
    -0.75
    €”
    -0.75
    POSITIVE LOGITS
    噸
    0.90
    مقدمه
    0.90
     mengapa
    0.84
     dilan
    0.83
     it
    0.82
    ◆◇
    0.77
     from
    0.76
     and
    0.76
     its
    0.74
    Spaghetti
    0.74
    Activations Density 0.002%

    No Known Activations