© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68695
    Prev
    Next
    INDEX
    Explanations

    end of lists

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

    The neuron is triggered by C pointer‐related code (pointer declarations, dereferences via “->”, NULL assignments, etc.).

    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
    entered
    -0.95
     contenedores
    -0.94
     причины
    -0.93
     bienes
    -0.89
    כום
    -0.88
     hermosos
    -0.87
     alrededores
    -0.86
     paisajes
    -0.86
     نہیں
    -0.85
    presumably
    -0.85
    POSITIVE LOGITS
    蕾
    1.00
     プリ
    0.93
    終わり
    0.90
    ăzi
    0.90
    ラク
    0.88
    輸送
    0.86
     посла
    0.85
     Weakness
    0.85
     there
    0.84
     cumbersome
    0.83
    Activations Density 0.002%

    No Known Activations