© 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. 203418
    Prev
    Next
    INDEX
    Explanations

    sales and administrative terms

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

    amplified, financial, desperate, discover

    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
    इंडियन
    0.52
    uerpo
    0.50
     সেগুলো
    0.50
    !);
    0.48
     அமெரிக்க
    0.46
    ë
    0.45
    !).
    0.45
    ולים
    0.45
    Dé
    0.45
    !!");
    0.44
    POSITIVE LOGITS
     sales
    0.48
     ket
    0.46
     administrative
    0.45
     clan
    0.45
     recruit
    0.45
     matches
    0.44
     revenue
    0.44
     feedstock
    0.43
     contact
    0.43
     kontrak
    0.43
    Activations Density 0.014%

    No Known Activations