© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36220
    Prev
    Next
    INDEX
    Explanations

    related to professions or occupations

    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_40_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
    З
    0.43
    וני
    0.41
    omyelitis
    0.40
    FFFFFF
    0.39
    clerotic
    0.38
    О
    0.38
     متحدہ
    0.38
    قتها
    0.38
    वीपी
    0.38
    FJ
    0.37
    POSITIVE LOGITS
    JobID
    0.39
    汥
    0.38
     domains
    0.38
     Skid
    0.38
     బె
    0.36
     obligations
    0.35
     occupations
    0.35
     processions
    0.35
     professions
    0.34
    Hrs
    0.34
    Activations Density 0.000%

    No Known Activations