© 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. 22-GEMMASCOPE-RES-131K
    7. 54146
    Prev
    Next
    INDEX
    Explanations

    solve for variable

    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
     to
    -1.00
     aquí
    -0.96
     lebron
    -0.94
    yled
    -0.93
    rédients
    -0.92
    icillin
    -0.90
     Як
    -0.90
     Merlot
    -0.90
     pakistan
    -0.88
    QB
    -0.87
    POSITIVE LOGITS
    dekat
    1.17
     estrena
    1.13
    Also
    1.12
     curiously
    1.10
     izquier
    1.10
     škoda
    1.08
     protectora
    1.06
     escuelas
    1.05
     wią
    1.05
    Carcinogenicity
    1.02
    Activations Density 0.040%

    No Known Activations