© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193246
    Prev
    Next
    INDEX
    Explanations

    cozy, cuddle, comforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    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
    leased
    0.48
     chlorophyll
    0.40
    出行
    0.40
    */)
    0.40
    fileID
    0.39
     frustrated
    0.38
    qid
    0.38
    awed
    0.38
    active
    0.38
    蚱
    0.38
    POSITIVE LOGITS
     cozy
    1.65
     cosy
    1.49
     Cozy
    1.41
     snug
    1.34
     уют
    1.22
     cuddling
    1.18
     cuddle
    1.15
     comfy
    1.07
     cudd
    1.04
     snugly
    1.02
    Activations Density 0.058%

    No Known Activations