© 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. 47347
    Prev
    Next
    INDEX
    Explanations

    on the place

    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
    halve
    -0.84
     propósito
    -0.82
     Biel
    -0.82
     กล
    -0.77
    ⣦
    -0.76
    一亮
    -0.75
     manera
    -0.75
     scripture
    -0.75
    пере
    -0.74
    defaults
    -0.73
    POSITIVE LOGITS
     scene
    1.06
     continent
    0.94
     docket
    0.90
     horizon
    0.88
     streets
    0.88
     island
    0.86
     circuit
    0.84
     hill
    0.81
     fence
    0.81
     cusp
    0.79
    Activations Density 0.057%

    No Known Activations