© 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. 192004
    Prev
    Next
    INDEX
    Explanations

    accordance with, concert of, avoid the, wife told

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

    `if` or `without` followed by `(` or `raising`

    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
     dej
    0.48
    cat
    0.43
    h
    0.42
    滅
    0.41
    ադ
    0.41
    avac
    0.41
     livet
    0.41
    采
    0.40
    جه
    0.40
     pij
    0.40
    POSITIVE LOGITS
     دوسرے
    0.45
     മണ്ണി
    0.44
     नेम
    0.43
     groceries
    0.43
    讳
    0.43
     उठ
    0.43
     Tuesdays
    0.42
     உரிய
    0.42
     सुगंध
    0.42
     lifts
    0.42
    Activations Density 0.000%

    No Known Activations