© 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. 114721
    Prev
    Next
    INDEX
    Explanations

    phrases following common prepositions

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

    social interaction scenarios

    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
     wicked
    0.48
     grat
    0.47
    誦
    0.46
     psychosis
    0.44
     الماده
    0.44
     subst
    0.43
     principe
    0.43
     mom
    0.43
     համ
    0.43
    鬱
    0.43
    POSITIVE LOGITS
    ن
    0.55
    하지만
    0.54
    st
    0.52
    b
    0.50
    v
    0.50
    m
    0.49
    이지만
    0.47
     –,
    0.47
    لم
    0.46
    w
    0.46
    Activations Density 0.000%

    No Known Activations