© 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. 401
    Prev
    Next
    INDEX
    Explanations

    models and calculations

    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
     lekker
    -1.32
    rechte
    -1.28
    springen
    -1.26
    İstin
    -1.22
     fokus
    -1.20
     เก
    -1.18
    mands
    -1.16
    verstanden
    -1.16
    hlar
    -1.14
    😿
    -1.14
    POSITIVE LOGITS
     calculations
    2.19
     estimate
    2.09
     calculation
    2.05
     estimates
    2.00
     for
    1.78
     analysis
    1.73
     estimated
    1.71
     calculate
    1.70
     based
    1.67
     calculated
    1.59
    Activations Density 0.067%

    No Known Activations