© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 164
    Prev
    Next
    INDEX
    Explanations

    Cornell University and associated systems

    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
     geometría
    0.43
     promete
    0.43
     offset
    0.42
     trono
    0.42
     promet
    0.42
     SBOM
    0.42
     garland
    0.41
    셍
    0.41
     zenith
    0.41
    బడు
    0.40
    POSITIVE LOGITS
    Cornell
    1.02
     Cornell
    0.95
     Ithaca
    0.75
    cornell
    0.61
    NYC
    0.49
     Corn
    0.48
    Corn
    0.47
     Ezra
    0.46
     NYC
    0.45
     corn
    0.43
    Activations Density 0.005%

    No Known Activations