© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69189
    Prev
    Next
    INDEX
    Explanations

    needed information or resources

    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
     posibles
    -0.91
     estructura
    -0.90
     kilomètres
    -0.89
     inversores
    -0.88
     posibilidades
    -0.86
    aneo
    -0.83
     potenciales
    -0.82
     propias
    -0.81
    ães
    -0.81
    ITOR
    -0.79
    POSITIVE LOGITS
     needed
    1.97
     need
    1.63
    needed
    1.47
    が必要
    1.45
     required
    1.39
     necessary
    1.30
     requirement
    1.23
    Needed
    1.19
     demand
    1.16
     Needed
    1.16
    Activations Density 0.193%

    No Known Activations