© 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. 193036
    Prev
    Next
    INDEX
    Explanations

    carpenter repairing

    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
     gasolina
    0.42
     suppliers
    0.42
     testosterone
    0.42
     deployments
    0.42
    ᕈ
    0.41
    क़
    0.40
    তাহাকে
    0.40
     hydrol
    0.40
     hydraz
    0.40
    িল্লী
    0.40
    POSITIVE LOGITS
    Flu
    0.42
    antu
    0.41
    de
    0.39
    Jon
    0.39
    룩
    0.38
    look
    0.38
     Cups
    0.38
    hen
    0.38
    flu
    0.38
    fl
    0.38
    Activations Density 0.000%

    No Known Activations