© 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. 10-GEMMASCOPE-RES-131K
    7. 21687
    Prev
    Next
    INDEX
    Explanations

    warmth and warm descriptions

    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_10/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
     できる
    -1.74
    hulk
    -1.66
    獰
    -1.63
    皷
    -1.56
     både
    -1.55
     himmel
    -1.48
     länder
    -1.47
    ܜ
    -1.47
    巂
    -1.45
     ferien
    -1.44
    POSITIVE LOGITS
     =
    1.68
    Warm
    1.65
     Warm
    1.61
    .
    1.59
     warm
    1.45
     Vereine
    1.45
     warmth
    1.43
    tels
    1.41
    ties
    1.38
    warm
    1.38
    Activations Density 0.016%

    No Known Activations