© 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. 91
    Prev
    Next
    INDEX
    Explanations

    acquaintances and friendships

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

    social relationships and acquaintances

    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
     ಸೂ
    0.50
     باستخدام
    0.42
     ಆಹಾರ
    0.41
     以
    0.40
    以
    0.39
     సూ
    0.39
     இயற்க
    0.38
     সংয
    0.38
     হ্রাস
    0.38
     各
    0.38
    POSITIVE LOGITS
     classmate
    0.62
     acquaint
    0.55
     acquaintance
    0.55
     근무
    0.52
     детства
    0.52
     uczest
    0.52
     pernah
    0.51
     acquaintances
    0.50
    曾在
    0.50
     познакоми
    0.50
    Activations Density 0.343%

    No Known Activations