© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98236
    Prev
    Next
    INDEX
    Explanations

    genetic programming, algorithms, headcount

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

    The neuron preferentially fires on standout domain‐specific content words—particularly legal‐boilerplate terms (claims, arising), algorithm names (Genetic), code identifiers/protocols (http, xmlns, controls), and other technical jargon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Away
    -0.71
     trương
    -0.71
    ahashi
    -0.68
    コロ
    -0.67
    嫉妒
    -0.66
    Could
    -0.66
     protested
    -0.66
    viewController
    -0.65
    eriam
    -0.64
    ロス
    -0.64
    POSITIVE LOGITS
    propylene
    0.70
    strateg
    0.68
    ляю
    0.68
    SCHEME
    0.68
    caffe
    0.65
     deadlines
    0.64
     Circuit
    0.64
     trả
    0.63
    winds
    0.63
    Circuit
    0.62
    Activations Density 0.061%

    No Known Activations