© 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. 9640
    Prev
    Next
    INDEX
    Explanations

    direction and position

    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
    在这里
    -1.05
     situation
    -0.99
    nemers
    -0.97
    ᄒ
    -0.96
    quartier
    -0.96
     doorstep
    -0.94
    โน
    -0.92
     biografias
    -0.91
    kirche
    -0.91
     küm
    -0.91
    POSITIVE LOGITS
     toward
    1.45
     towards
    1.43
     into
    1.36
    toward
    1.28
    towards
    1.02
     until
    0.99
     hacia
    0.96
     течение
    0.94
     قناة
    0.93
     Toward
    0.91
    Activations Density 0.135%

    No Known Activations