© 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. 34-GEMMASCOPE-RES-131K
    7. 99540
    Prev
    Next
    INDEX
    Explanations

    legislative or medical terms

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

    numeric year patterns (dates) in the format of individual numbers (like 2, 0, 1, 3).

    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_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
    שׁ
    -0.85
     METHODOLOGY
    -0.82
    يح
    -0.77
    refs
    -0.77
    詩
    -0.75
    課
    -0.75
    tritt
    -0.73
     decided
    -0.73
    氣
    -0.72
    ゅ
    -0.72
    POSITIVE LOGITS
     otherwise
    0.90
     grà
    0.89
    Otherwise
    0.84
    heiser
    0.78
     создать
    0.77
    eseed
    0.77
    ButtonGroup
    0.76
     altrimenti
    0.75
     secluded
    0.75
     enorm
    0.74
    Activations Density 0.012%

    No Known Activations