© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72357
    Prev
    Next
    INDEX
    Explanations

    viewDidLoad or onCreate

    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_22/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
     blusas
    -1.51
     individuelles
    -1.25
    bentuk
    -1.23
     enfrentan
    -1.18
     Wartawan
    -1.18
     indivíduo
    -1.13
     pretože
    -1.13
     olivat
    -1.12
    vacy
    -1.10
     Atención
    -1.10
    POSITIVE LOGITS
     this
    1.48
    瀦
    1.09
     will
    1.03
     parcheggio
    1.02
     services
    1.00
    )];
    0.98
    𝒙
    0.94
     further
    0.94
     spiaggia
    0.93
     while
    0.93
    Activations Density 0.006%

    No Known Activations