© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33921
    Prev
    Next
    INDEX
    Explanations

    comfort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probes
    0.41
     choking
    0.40
    グラム
    0.39
     susp
    0.39
     hardworking
    0.39
    susp
    0.39
    SUR
    0.38
    江
    0.38
     mutations
    0.38
     Ober
    0.37
    POSITIVE LOGITS
     comfort
    0.96
     comforted
    0.91
     confort
    0.90
     комфор
    0.88
    Comfort
    0.88
     Comfort
    0.85
     conforto
    0.84
    comfort
    0.82
     comforts
    0.82
     comforting
    0.79
    Activations Density 0.001%

    No Known Activations