© 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. 72063
    Prev
    Next
    INDEX
    Explanations

    collective entities and specific descriptions

    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
     welchem
    -0.79
    нен
    -0.78
     Blu
    -0.74
     Ceramby
    -0.74
    ื่น
    -0.73
    Southern
    -0.73
     Josef
    -0.72
    †
    -0.71
     Berkeley
    -0.71
    University
    -0.71
    POSITIVE LOGITS
    collective
    0.90
     collective
    0.86
     community
    0.85
    行った
    0.84
    țiilor
    0.81
    Redaktion
    0.81
     admin
    0.80
    Interes
    0.80
    Existe
    0.80
    Collective
    0.77
    Activations Density 0.112%

    No Known Activations