© 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. 116815
    Prev
    Next
    INDEX
    Explanations

    invisible, dummy, or temporary

    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
     undecided
    -0.79
     Everton
    -0.76
    Presenting
    -0.75
     Zn
    -0.75
    roffene
    -0.72
    ices
    -0.71
     podľa
    -0.71
     cập
    -0.69
    вли
    -0.69
     Anderson
    -0.68
    POSITIVE LOGITS
    tempor
    1.09
     dummy
    1.06
    Invisible
    1.02
     Invisible
    0.98
     invisible
    0.96
    Tempor
    0.94
    INVISIBLE
    0.93
    forcing
    0.93
     temporary
    0.85
    临时
    0.84
    Activations Density 0.043%

    No Known Activations