© 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. 73482
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

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

    The neuron fires on segments of fully qualified package or class names (e.g. the dotted import path tokens in Java/Android 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
     candidatura
    -1.15
     geografia
    -1.13
    vaného
    -1.05
    vaných
    -1.03
     piscina
    -1.02
     ostensibly
    -1.00
    bildning
    -1.00
     determina
    -0.97
     сахара
    -0.96
    ائدة
    -0.96
    POSITIVE LOGITS
     участники
    1.02
    }:
    0.98
     مجرد
    0.98
     -
    0.97
     secado
    0.94
     звука
    0.94
    设置
    0.94
    が少ない
    0.94
     sugerencias
    0.94
     oferecer
    0.93
    Activations Density 0.004%

    No Known Activations