© 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. 50320
    Prev
    Next
    INDEX
    Explanations

    choice or selection words

    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
    itze
    -0.96
    ConstraintSet
    -0.93
    ׄ
    -0.93
    ólicos
    -0.91
    zação
    -0.90
    šak
    -0.88
    umbo
    -0.88
    ocumented
    -0.86
    keyup
    -0.86
    ík
    -0.85
    POSITIVE LOGITS
     choose
    6.53
     chosen
    6.16
     choosing
    6.00
     chose
    5.78
     choice
    5.69
     chooses
    5.66
     selected
    5.38
    选择
    5.31
    choose
    5.22
     chọn
    5.22
    Activations Density 0.439%

    No Known Activations