© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47363
    Prev
    Next
    INDEX
    Explanations

    removing or hiding elements

    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
     impersonal
    -0.83
     oseb
    -0.82
     Orgel
    -0.78
    etzung
    -0.76
     prič
    -0.73
    Personal
    -0.73
     restruct
    -0.72
    IFI
    -0.71
     tylko
    -0.71
     Personal
    -0.71
    POSITIVE LOGITS
     removeFrom
    1.87
    removeFrom
    1.74
     disappears
    1.63
     disappeared
    1.52
     removed
    1.51
     disappear
    1.50
     removal
    1.46
     remove
    1.42
    remove
    1.39
     vanishes
    1.32
    Activations Density 0.009%

    No Known Activations