© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 224368
    Prev
    Next
    INDEX
    Explanations

    hugs and embraces

    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
    beauty
    0.47
     etching
    0.44
     beauty
    0.42
     உச்ச
    0.41
     ತು
    0.41
    ṓ
    0.40
     Beauty
    0.39
    Parliament
    0.39
    喃
    0.38
     ات
    0.38
    POSITIVE LOGITS
     hug
    1.39
     hugs
    1.39
     hugging
    1.36
     hugged
    1.36
     Hug
    1.11
    hug
    1.02
    Hug
    0.96
     abrazo
    0.92
    抱
    0.77
     abraz
    0.73
    Activations Density 0.021%

    No Known Activations