© 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. 62822
    Prev
    Next
    INDEX
    Explanations

    amp; and android: attributes

    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
     even
    -1.04
     around
    -0.98
     despite
    -0.95
     more
    -0.94
     having
    -0.82
     especially
    -0.82
     by
    -0.79
    ebenarnya
    -0.79
     in
    -0.78
    فره
    -0.78
    POSITIVE LOGITS
     amput
    0.93
     afore
    0.87
     alluring
    0.85
     individuality
    0.85
    AMP
    0.84
    *;
    0.83
    Asoci
    0.82
    是不
    0.81
     portables
    0.80
     mutil
    0.80
    Activations Density 0.001%

    No Known Activations