© 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. 93633
    Prev
    Next
    INDEX
    Explanations

    questions and offers

    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
     conspic
    -0.84
     Philos
    -0.82
     Afric
    -0.81
     suscepti
    -0.80
     Salty
    -0.79
     costumi
    -0.77
     Greedy
    -0.77
    כונה
    -0.77
     SOUL
    -0.77
    sólo
    -0.77
    POSITIVE LOGITS
     Multi
    0.79
     Pop
    0.78
     go
    0.78
     emperador
    0.77
    activated
    0.76
    駅から
    0.76
    selectable
    0.75
     $$
    0.74
    popup
    0.72
     Ind
    0.71
    Activations Density 0.005%

    No Known Activations