© 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. 117158
    Prev
    Next
    INDEX
    Explanations

    thickening and binding agents

    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
    Concentr
    -0.82
     especí
    -0.77
     configuración
    -0.73
    DK
    -0.73
    ghted
    -0.71
    строен
    -0.69
     Gründer
    -0.68
    Frans
    -0.68
     obrá
    -0.68
    foreground
    -0.68
    POSITIVE LOGITS
     thickening
    2.09
     binder
    1.80
     thicken
    1.70
     binding
    1.67
     binders
    1.65
     thick
    1.47
    binding
    1.44
    thick
    1.37
     stabilizer
    1.36
     Thick
    1.35
    Activations Density 0.070%

    No Known Activations