© 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. 22-GEMMASCOPE-RES-131K
    7. 129382
    Prev
    Next
    INDEX
    Explanations

    android app activity extends

    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_22/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
     varför
    -1.04
    ">—
    -1.03
    子さん
    -1.01
     from
    -0.99
     команди
    -0.97
     LLC
    -0.94
    NSNumber
    -0.94
    omás
    -0.93
     Reisen
    -0.93
    骧
    -0.93
    POSITIVE LOGITS
     RESPOND
    0.98
     commande
    0.97
    emphas
    0.96
     Récup
    0.94
     diriger
    0.93
    complicated
    0.91
    блок
    0.88
    commented
    0.87
    simult
    0.85
    trying
    0.85
    Activations Density 0.032%

    No Known Activations