© 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. 59805
    Prev
    Next
    INDEX
    Explanations

    out to or away

    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
     clín
    -0.79
     uphill
    -0.77
    ashing
    -0.75
    anstalt
    -0.74
    ucid
    -0.73
     quai
    -0.72
    quées
    -0.69
     out
    -0.69
    iC
    -0.69
     outnumbered
    -0.69
    POSITIVE LOGITS
     into
    1.11
    iterraneo
    0.78
    海老
    0.78
     Chen
    0.74
    ğan
    0.73
    ficulty
    0.69
     superstition
    0.69
    到
    0.68
    kir
    0.68
    mix
    0.68
    Activations Density 0.026%

    No Known Activations