© 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. 107708
    Prev
    Next
    INDEX
    Explanations

    wireless communication systems

    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
     Lush
    -0.77
    
    -0.77
    λλην
    -0.77
    itra
    -0.75
    cionar
    -0.73
    Ⓚ
    -0.73
     personalise
    -0.73
    íts
    -0.71
    kovi
    -0.71
    caris
    -0.71
    POSITIVE LOGITS
     transference
    0.72
     EPS
    0.71
     Jewelry
    0.71
     Subject
    0.69
     poetry
    0.69
     Securities
    0.69
     Columbus
    0.69
     NAS
    0.68
     transport
    0.68
     Recovery
    0.68
    Activations Density 0.019%

    No Known Activations