© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7972
    Prev
    Next
    INDEX
    Explanations

    love activities or things

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

    expressing preferences or interests

    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_31_width_262k_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
    s
    0.28
     ادار
    0.26
    സ്
    0.25
     اع
    0.25
     सर्वि
    0.25
    淫
    0.24
    点
    0.24
    തിരെ
    0.23
    𝙋
    0.23
    ꜰ
    0.23
    POSITIVE LOGITS
     dearly
    0.36
    uste
    0.32
     to
    0.31
     chatting
    0.29
     reading
    0.29
     experimenting
    0.28
     работать
    0.28
     trabajar
    0.27
     enjoyed
    0.27
    so
    0.27
    Activations Density 0.188%

    No Known Activations