© 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. 119231
    Prev
    Next
    INDEX
    Explanations

    verbs followed by up or out

    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
     Away
    -0.92
    .},
    -0.90
    getSimpleName
    -0.84
    Away
    -0.82
     AWAY
    -0.80
     kommit
    -0.79
     esteja
    -0.79
     株
    -0.78
    dá
    -0.77
    ricts
    -0.75
    POSITIVE LOGITS
     up
    0.91
     out
    0.84
    Gina
    0.83
    innung
    0.82
     ได้
    0.79
     Phần
    0.78
     denkt
    0.77
    是怎么回事
    0.77
     还
    0.76
    uaire
    0.75
    Activations Density 0.085%

    No Known Activations