© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3821
    Prev
    Next
    INDEX
    Explanations

    Introduction to a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    adecimal
    2.27
     constituents
    2.24
     mainland
    2.21
     respective
    2.20
    ी
    2.19
    
    2.16
     qualitative
    2.16
     surjective
    2.14
     coastal
    2.13
     intended
    2.12
    POSITIVE LOGITS
    Untuk
    2.44
    Pada
    2.29
    Không
    2.22
     하지
    2.22
     ไม่มี
    2.16
    Tidak
    2.16
    Selain
    2.14
    To
    2.13
    멈
    2.13
    Jika
    2.11
    Activations Density 0.000%

    No Known Activations