© 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. 16-GEMMASCOPE-2-RES-16K
    7. 576
    Prev
    Next
    INDEX
    Explanations

    announcements and opportunities

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

    requests and instructions

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

    period

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
     circumference
    0.33
     व
    0.32
     بر
    0.32
     من
    0.31
     с
    0.31
     pecan
    0.30
     blouse
    0.30
     cheery
    0.30
     ла
    0.30
     saucepan
    0.30
    POSITIVE LOGITS
    YOU
    0.33
    You
    0.32
    ,
    0.31
    Industry
    0.31
    Ako
    0.30
    Advice
    0.30
     interesado
    0.30
    Development
    0.29
    HAN
    0.29
    或者
    0.29
    Activations Density 0.000%

    No Known Activations