© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91137
    Prev
    Next
    INDEX
    Explanations

    Ka/C followed by 'unas', 'agnic', 'Tak', 'ifu', 'kegawa', 'kheti', 'dix', 'laip', 'tete', 'rnak', 'lving'

    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
     Vamos
    -0.79
    が
    -0.78
     however
    -0.78
    それでは
    -0.75
    ってみる
    -0.74
    旅館
    -0.73
    小心翼翼
    -0.71
    労
    -0.71
     Silly
    -0.71
     sendero
    -0.70
    POSITIVE LOGITS
    ときの
    0.84
    のではなく
    0.77
    狀
    0.76
    inctions
    0.74
    場合には
    0.73
    ազմ
    0.73
    になりたい
    0.72
    มาะ
    0.71
    えて
    0.71
     Deloitte
    0.71
    Activations Density 0.047%

    No Known Activations