© 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. 103710
    Prev
    Next
    INDEX
    Explanations

    LINQ methods

    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
     Vesta
    -0.79
    )}_
    -0.71
     vē
    -0.70
    ဂ
    -0.69
    matrices
    -0.67
    geolocation
    -0.66
    dft
    -0.66
     Gatsby
    -0.66
    trop
    -0.66
    にあ
    -0.66
    POSITIVE LOGITS
     LIN
    2.78
    LIN
    2.59
    Linq
    2.56
     Lin
    2.20
     lin
    2.03
     lambda
    1.96
    lin
    1.89
    Lin
    1.84
    lambda
    1.77
    Queryable
    1.76
    Activations Density 0.220%

    No Known Activations