© 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. 83297
    Prev
    Next
    INDEX
    Explanations

    invalid initialization, undefined, symbols

    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
     provato
    -0.79
     hook
    -0.77
     skor
    -0.75
    élev
    -0.72
    @{
    -0.71
    gespräch
    -0.71
    Parte
    -0.70
     Stalker
    -0.69
     hooks
    -0.69
     anivers
    -0.68
    POSITIVE LOGITS
     HRC
    0.70
    ⁡
    0.69
    CoA
    0.69
    ТР
    0.68
    ーブ
    0.67
    ба
    0.66
    नि
    0.66
    +:+
    0.66
    éu
    0.64
     influx
    0.64
    Activations Density 0.075%

    No Known Activations