© 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. 67491
    Prev
    Next
    INDEX
    Explanations

    organizational roles and positions

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

    professional job titles

    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
    गण
    0.46
    謁
    0.45
    精神
    0.45
    養成
    0.44
    日在
    0.44
     აღ
    0.43
    ವಾಸ
    0.42
    擄
    0.42
    Challenges
    0.41
    勵
    0.41
    POSITIVE LOGITS
    phalt
    0.48
     ricotta
    0.47
     这
    0.46
     isset
    0.45
     iridium
    0.45
    ☘
    0.45
     Với
    0.44
     sawing
    0.44
     isopropyl
    0.43
     Sauer
    0.43
    Activations Density 0.039%

    No Known Activations