© 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. 64209
    Prev
    Next
    INDEX
    Explanations

    damp, moist, wet, humid

    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
     known
    -0.88
     know
    -0.87
     Sonn
    -0.81
    に伴
    -0.81
    を行い
    -0.76
    loyee
    -0.75
     psychologie
    -0.74
    getUrl
    -0.73
    bliž
    -0.73
     групи
    -0.71
    POSITIVE LOGITS
    damp
    1.37
     damp
    1.32
     Damp
    1.27
    ened
    1.19
    ening
    1.07
    ness
    1.05
    Wet
    1.03
     humid
    1.02
     wet
    1.01
    wet
    1.00
    Activations Density 0.015%

    No Known Activations