© 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. 59814
    Prev
    Next
    INDEX
    Explanations

    -ing and -ize endings

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

    Characters, country, conflict, continued

    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
     meriye
    0.54
    UpSync
    0.53
    нави
    0.51
    ที
    0.50
     }</
    0.50
    帜
    0.49
    Subgraph
    0.49
     নির্ম
    0.48
     ఓ
    0.48
    }.$$
    0.48
    POSITIVE LOGITS
    yt
    0.61
    ding
    0.55
    bs
    0.52
    df
    0.52
    yo
    0.52
    .
    0.48
    ialize
    0.45
    issimus
    0.45
    ugia
    0.44
    dinga
    0.44
    Activations Density 0.001%

    No Known Activations