© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2862
    Prev
    Next
    INDEX
    Explanations

    dog destructive behavior

    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
    瘫
    -0.88
     "&
    -0.83
    EnableWeb
    -0.82
     animal
    -0.82
     pets
    -0.81
     animals
    -0.81
    namics
    -0.80
    érité
    -0.78
     animales
    -0.77
     Hayat
    -0.77
    POSITIVE LOGITS
     destructive
    1.27
     chewing
    1.25
     chew
    1.18
    destructive
    1.13
     chewed
    1.06
     Separation
    1.04
     destruction
    1.03
     separation
    1.02
    separation
    1.02
     destroy
    0.98
    Activations Density 0.016%

    No Known Activations