© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55446
    Prev
    Next
    INDEX
    Explanations

    salesperson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rägen
    0.51
     দুর্ভোগ
    0.50
    比べて
    0.46
     sozialen
    0.45
    ަށް
    0.45
     favore
    0.44
     മ
    0.43
     비교
    0.43
     രോഗ
    0.43
     miejsc
    0.43
    POSITIVE LOGITS
    或者是
    0.44
     salesperson
    0.44
     nominated
    0.43
     bahkan
    0.42
    เคย
    0.42
     salespeople
    0.41
     salesmen
    0.41
     Jonas
    0.40
     salesman
    0.40
     Joni
    0.40
    Activations Density 0.006%

    No Known Activations