© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11173
    Prev
    Next
    INDEX
    Explanations

    mascara and eyelashes

    np_acts-logits-general · gemini-2.5-flash-lite

    curling eyelashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     банки
    0.42
    腦
    0.42
    ầng
    0.40
    ន៍
    0.39
    າກ
    0.38
    㷫
    0.38
    NAMEN
    0.38
    Decrypt
    0.37
     банков
    0.37
    ENIDO
    0.37
    POSITIVE LOGITS
     eyelashes
    1.37
     lashes
    1.28
     eyelash
    1.28
     lash
    1.26
    睫
    1.26
     Lash
    1.14
     lashed
    1.05
     mascara
    0.95
     curling
    0.94
    lashes
    0.93
    Activations Density 0.249%

    No Known Activations