© 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. 6491
    Prev
    Next
    INDEX
    Explanations

    forming friendships and relationships

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

    creation, growth, and potential

    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
     এরূপ
    0.55
     any
    0.48
     উক্ত
    0.47
    /
    0.47
     annoying
    0.47
     wastage
    0.46
     সর্বদা
    0.46
    任何
    0.46
    基本的に
    0.45
     Generally
    0.45
    POSITIVE LOGITS
     буквально
    0.59
     literalmente
    0.55
     하늘
    0.53
     inesper
    0.53
     новых
    0.50
    ﻟ
    0.49
    נג
    0.49
    ใหม่
    0.49
     nuovi
    0.49
     amidst
    0.48
    Activations Density 0.018%

    No Known Activations