© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25114
    Prev
    Next
    INDEX
    Explanations

    cute and baby-like things

    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_all/layer_41_width_262k_l0_big
    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
    Shroud
    0.48
    👠
    0.46
    🌒
    0.44
    🥀
    0.43
    𐰣
    0.43
    🦅
    0.42
    🔃
    0.42
    🕖
    0.42
     युवती
    0.42
    🕗
    0.41
    POSITIVE LOGITS
     cute
    1.95
     adorable
    1.87
     Cute
    1.76
    cute
    1.72
    Cute
    1.68
     cutest
    1.63
    可爱
    1.49
    adorable
    1.49
    可愛
    1.47
    Adorable
    1.45
    Activations Density 0.008%

    No Known Activations