© 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. 64970
    Prev
    Next
    INDEX
    Explanations

    retrospective review

    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
    实验
    -0.92
     slä
    -0.87
     smiled
    -0.85
    republik
    -0.85
     Experiments
    -0.79
     both
    -0.78
    州市
    -0.77
    Geschiedenis
    -0.76
     several
    -0.75
     experimentation
    -0.75
    POSITIVE LOGITS
     retrospective
    1.89
     prospec
    1.88
     retrospec
    1.71
    retro
    1.53
     cohort
    1.51
     Retrospective
    1.48
     prospective
    1.41
    Retro
    1.39
     consecutive
    1.32
     cohorts
    1.20
    Activations Density 0.896%

    No Known Activations