© 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. 34-GEMMASCOPE-RES-131K
    7. 58626
    Prev
    Next
    INDEX
    Explanations

    target string search

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

    The neuron fires most strongly on integer‐related tokens in code—especially the “int” type keyword (and accompanying numeric literals or array‐of‐int notation).

    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
     onOptions
    -0.90
    鮭
    -0.84
     characteristics
    -0.80
    kir
    -0.77
    mist
    -0.73
     デジタル
    -0.72
    OneToOne
    -0.72
     JMenuItem
    -0.71
    詠
    -0.71
    grunt
    -0.71
    POSITIVE LOGITS
     target
    1.80
    target
    1.35
     Target
    1.31
     K
    1.28
     k
    1.25
    目標
    1.20
    Target
    1.18
    目标
    1.14
    TARGET
    1.09
     goal
    1.08
    Activations Density 0.048%

    No Known Activations