© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109825
    Prev
    Next
    INDEX
    Explanations

    replacement and exchange

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    esinde
    -0.92
    Inheritance
    -0.79
    ลา
    -0.78
     leases
    -0.75
     lateinit
    -0.74
     안
    -0.73
    izando
    -0.73
     liber
    -0.73
    解放
    -0.73
    oretical
    -0.72
    POSITIVE LOGITS
     replacement
    3.28
     replacements
    2.95
     replace
    2.75
    Replacement
    2.56
    replacement
    2.55
     replaced
    2.53
    replace
    2.48
     Replacement
    2.45
     replacing
    2.42
    Replace
    2.19
    Activations Density 0.016%

    No Known Activations