© 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. 34-GEMMASCOPE-RES-131K
    7. 48493
    Prev
    Next
    INDEX
    Explanations

    booking, reserving, and securing

    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
    LOADED
    -0.79
    丁
    -0.72
    شير
    -0.70
    ਹ
    -0.70
    positorio
    -0.70
     پذ
    -0.70
    kosti
    -0.69
    હ
    -0.69
    cán
    -0.68
     reception
    -0.67
    POSITIVE LOGITS
     reserve
    2.81
     secures
    2.67
     reserving
    2.59
     reserved
    2.56
    reserve
    2.52
     securing
    2.39
    Reserve
    2.30
     secure
    2.27
     secured
    2.20
     reserves
    2.16
    Activations Density 0.036%

    No Known Activations