© 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. 34-GEMMASCOPE-RES-131K
    7. 98849
    Prev
    Next
    INDEX
    Explanations

    splashed

    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
    Anchor
    -0.87
     raped
    -0.86
    KILL
    -0.83
    RSS
    -0.83
    kill
    -0.82
    insert
    -0.80
    Insert
    -0.79
     Blut
    -0.79
    Place
    -0.75
     murderers
    -0.75
    POSITIVE LOGITS
     sprayed
    1.36
     splash
    1.34
     Splash
    1.29
     splashed
    1.27
     splashing
    1.22
     prank
    1.19
     spray
    1.18
    splash
    1.16
    Splash
    1.10
     spraying
    1.09
    Activations Density 0.024%

    No Known Activations