© 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. 109852
    Prev
    Next
    INDEX
    Explanations

    expire and expiry

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

    terms and phrases related to contract expiration or renewal.

    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
     Micha
    -0.77
    दी
    -0.73
    xido
    -0.72
     fellowships
    -0.69
    eramente
    -0.69
    ជ
    -0.69
    唧
    -0.69
    カー
    -0.69
    cesz
    -0.68
    osamente
    -0.68
    POSITIVE LOGITS
     expire
    5.00
     expires
    4.91
     expired
    4.84
     expiration
    3.80
     expiry
    3.75
    expire
    3.70
     expiring
    3.67
    Expire
    3.66
    expired
    3.53
    expires
    3.39
    Activations Density 0.086%

    No Known Activations