© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57626
    Prev
    Next
    INDEX
    Explanations

    lifetime and life

    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
    段时间
    -0.74
    титься
    -0.66
    ური
    -0.65
    ფ
    -0.65
    JOE
    -0.65
    وروب
    -0.65
    paraíso
    -0.64
     בְּ
    -0.63
     Francis
    -0.63
    itectura
    -0.63
    POSITIVE LOGITS
     lifetime
    6.97
     lifelong
    6.19
    lifetime
    5.63
    Lifetime
    5.34
     Lifetime
    5.34
     lifetimes
    3.98
     LIF
    3.70
    LIF
    3.59
    一生
    3.11
     life
    3.02
    Activations Density 0.149%

    No Known Activations