© 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. 118614
    Prev
    Next
    INDEX
    Explanations

    gone offline

    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
     riport
    -0.81
    覗
    -0.81
     parity
    -0.78
     चे
    -0.78
     ranting
    -0.71
    olar
    -0.71
    ƴ
    -0.71
    พาะ
    -0.70
    AppService
    -0.70
     unterscheidet
    -0.70
    POSITIVE LOGITS
     ghost
    2.72
    ghost
    2.48
    Ghost
    2.23
     Ghost
    2.14
     disappeared
    2.13
     disappear
    1.98
     silence
    1.92
     disappearing
    1.88
     disappears
    1.80
     ghosts
    1.70
    Activations Density 0.032%

    No Known Activations