© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55642
    Prev
    Next
    INDEX
    Explanations

    free from something

    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
     insufic
    -0.89
     zug
    -0.81
     Auß
    -0.76
    nthetic
    -0.75
    了出去
    -0.71
    ToEdit
    -0.71
    قت
    -0.70
     lieber
    -0.69
     وتسجيلات
    -0.68
    chastic
    -0.68
    POSITIVE LOGITS
     free
    4.88
    free
    3.94
     devoid
    3.39
    Free
    3.14
     Free
    3.00
    FREE
    2.70
     свобод
    2.59
     FREE
    2.58
     freed
    2.50
     bebas
    2.48
    Activations Density 0.220%

    No Known Activations