© 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. 90907
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    fff
    -0.82
    𝐹
    -0.76
    いわゆる
    -0.75
     small
    -0.75
    牟
    -0.74
    廳
    -0.73
    osex
    -0.71
     Lancaster
    -0.70
    uties
    -0.70
    филь
    -0.69
    POSITIVE LOGITS
    Reported
    0.96
    pédie
    0.89
     laço
    0.82
    voegen
    0.81
     盒
    0.78
     Espagne
    0.76
     Inſ
    0.75
    reported
    0.75
     interi
    0.75
    ukup
    0.74
    Activations Density 0.000%

    No Known Activations