© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47974
    Prev
    Next
    INDEX
    Explanations

    metric and unit suffixes

    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
     pencil
    -0.82
     lệ
    -0.80
    ヶ
    -0.79
     Cupid
    -0.74
    ً
    -0.71
     Integrative
    -0.71
     каже
    -0.70
    Boxscore
    -0.68
     rainbows
    -0.68
     maxlength
    -0.67
    POSITIVE LOGITS
    Units
    1.26
     suffixes
    1.20
     units
    1.18
    Suffix
    1.09
    suffix
    1.09
    human
    1.09
    Metric
    1.06
    UNITS
    1.05
    IEC
    1.04
    Unit
    1.02
    Activations Density 0.028%

    No Known Activations