© 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. 16-GEMMASCOPE-2-RES-262K
    7. 32322
    Prev
    Next
    INDEX
    Explanations

    doll, dollhouse, doll-like

    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_16_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
    ה
    1.59
    a
    1.58
    ه
    1.28
    .
    1.18
    ,
    1.16
    ت
    1.05
    ):
    1.03
    =
    1.03
    る
    1.03
    ۔
    1.02
    POSITIVE LOGITS
     It
    1.12
     Doll
    1.09
    ெட்
    0.96
    ė
    0.95
     Barcelone
    0.90
    ことは
    0.89
     Himachal
    0.88
    ě
    0.86
    ான்
    0.85
    加え
    0.84
    Activations Density 0.001%

    No Known Activations