© 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. 37752
    Prev
    Next
    INDEX
    Explanations

    whether or if

    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
     what
    -1.27
     how
    -1.15
     only
    -0.91
    Where
    -0.91
    どんな
    -0.89
     not
    -0.88
     Those
    -0.88
     только
    -0.87
     strictly
    -0.85
     some
    -0.84
    POSITIVE LOGITS
    ther
    1.76
     whether
    1.38
    ither
    1.16
    ather
    1.01
    THER
    0.98
    ether
    0.93
    ETHER
    0.90
    Composición
    0.87
     سواء
    0.85
     wither
    0.85
    Activations Density 0.058%

    No Known Activations