© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    require cancellation or problem

    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
     Rumah
    -0.85
    vinyl
    -0.83
     isolé
    -0.81
     gale
    -0.79
     cio
    -0.79
     bli
    -0.78
     roberto
    -0.78
     lefs
    -0.77
     Colette
    -0.77
     fep
    -0.77
    POSITIVE LOGITS
     stabilize
    0.94
     realize
    0.82
     Mechanism
    0.81
     ύ
    0.80
     Problem
    0.79
    imc
    0.78
     runaway
    0.78
     pillars
    0.77
     realizes
    0.77
     realise
    0.77
    Activations Density 0.043%

    No Known Activations