© 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. 13160
    Prev
    Next
    INDEX
    Explanations

    applied to options

    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
     commenced
    -0.90
    Introductory
    -0.88
    utama
    -0.82
    municipi
    -0.79
    angun
    -0.79
    sprzedam
    -0.78
    ᴴ
    -0.77
     merusak
    -0.76
    國內
    -0.76
    inchen
    -0.75
    POSITIVE LOGITS
     replicated
    0.97
    Apply
    0.92
    ReusableCell
    0.92
     APPLIED
    0.89
    Merge
    0.88
    UTC
    0.88
     applied
    0.87
     apply
    0.86
    Match
    0.85
     applies
    0.84
    Activations Density 0.070%

    No Known Activations