© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48184
    Prev
    Next
    INDEX
    Explanations

    stone and walls

    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_34/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
     Ansel
    -0.83
     marshes
    -0.80
    ETO
    -0.80
    cdi
    -0.78
    反應
    -0.77
     Fij
    -0.77
     รัก
    -0.75
     Reporters
    -0.73
     कीजिए
    -0.73
    bulan
    -0.73
    POSITIVE LOGITS
     stone
    2.09
     wall
    1.60
    stone
    1.59
     stones
    1.54
    Stone
    1.45
    石
    1.41
     piedra
    1.37
    wall
    1.36
     Stone
    1.34
    STONE
    1.34
    Activations Density 0.023%

    No Known Activations