© 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. 30912
    Prev
    Next
    INDEX
    Explanations

    mobile phones

    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
     first
    -1.02
     being
    -0.98
     it
    -0.94
     September
    -0.91
     Before
    -0.87
     enough
    -0.85
    pous
    -0.82
     before
    -0.81
    Before
    -0.81
     what
    -0.80
    POSITIVE LOGITS
    绞
    0.90
    יע
    0.88
     TextAppearance
    0.83
    anthemum
    0.83
     convi
    0.80
    uch
    0.77
    ek
    0.77
     الصور
    0.76
    Followers
    0.76
    bücher
    0.76
    Activations Density 0.009%

    No Known Activations