© 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. 125332
    Prev
    Next
    INDEX
    Explanations

    verb phrases like "pushed down"

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

    driven by needs

    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
    zip
    0.50
    ويه
    0.48
     a
    0.46
     expresar
    0.46
    s
    0.46
     dfs
    0.46
     h
    0.46
     Brat
    0.46
     fl
    0.45
     q
    0.45
    POSITIVE LOGITS
     भुगतान
    0.54
     เนื่อง
    0.50
    poli
    0.48
     जेव्हा
    0.47
    期间
    0.46
     chút
    0.45
    几天
    0.45
    付款
    0.45
     통해서
    0.45
     ભારે
    0.44
    Activations Density 0.000%

    No Known Activations