© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102931
    Prev
    Next
    INDEX
    Explanations

    owner, owned, frontage, pricing, hosts, tickets

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

    owned

    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
    Negative Logits
     infección
    0.55
     positivas
    0.47
    ڊ
    0.46
     cadrul
    0.45
    設定
    0.45
     variado
    0.45
    輙
    0.45
     variáveis
    0.44
     governador
    0.43
     efficacement
    0.43
    POSITIVE LOGITS
     주
    0.51
     owned
    0.50
     taxable
    0.49
     অন্যের
    0.49
    Owner
    0.48
     USD
    0.47
    Owners
    0.47
     Owner
    0.47
     Owned
    0.46
     frontage
    0.45
    Activations Density 0.005%

    No Known Activations