© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101341
    Prev
    Next
    INDEX
    Explanations

    target compounds and sequences

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

    references to target elements in code or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -1.81
     We
    -1.68
    8
    -1.67
                
    -1.48
    ("
    -1.45
    9
    -1.43
     apparaissent
    -1.42
     اصلا
    -1.38
    鶿
    -1.37
    with
    -1.36
    POSITIVE LOGITS
    ’
    1.52
    ==$
    1.48
    يكي
    1.48
     targeted
    1.47
     Она
    1.41
    しまった
    1.41
     problemen
    1.38
     compuestos
    1.35
    .}(
    1.34
    
    1.34
    Activations Density 0.034%

    No Known Activations