© 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. 58408
    Prev
    Next
    INDEX
    Explanations

    employee area; of some

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

    requiring or mandating business actions

    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
    jsoup
    0.49
    चार
    0.44
    pubmed
    0.43
    лом
    0.41
    зки
    0.41
    πον
    0.41
    選舉
    0.41
    𝐚
    0.41
    νομ
    0.40
     soch
    0.40
    POSITIVE LOGITS
     bluntly
    0.48
     explicitly
    0.45
     eyep
    0.43
    Setelah
    0.42
     designs
    0.42
     hybridization
    0.42
     flourishes
    0.42
     Indonesian
    0.41
     Inj
    0.41
     būti
    0.41
    Activations Density 0.000%

    No Known Activations