© 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. 63644
    Prev
    Next
    INDEX
    Explanations

    responsive mobile

    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
    ധ
    -0.96
    غب
    -0.85
    кій
    -0.84
     zonas
    -0.84
     protects
    -0.82
    PictureBox
    -0.82
    mlink
    -0.82
     linked
    -0.81
    toupper
    -0.81
    onymy
    -0.81
    POSITIVE LOGITS
     mobile
    1.82
     Mobile
    1.65
     MOBILE
    1.59
    Mobile
    1.48
    mobile
    1.42
    Responsive
    1.37
     resize
    1.36
     адап
    1.34
     responsive
    1.34
     Responsive
    1.33
    Activations Density 0.106%

    No Known Activations