© 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. 90544
    Prev
    Next
    INDEX
    Explanations

    certain animals

    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
    㕸
    0.52
    studentRecord
    0.47
     BECAUSE
    0.47
    ವರಿಗೆ
    0.46
    oarece
    0.46
    ᱙
    0.46
    splitted
    0.45
     inorder
    0.45
     morales
    0.45
    絠
    0.45
    POSITIVE LOGITS
    0.54
     Stet
    0.48
     Minecraft
    0.48
     DIY
    0.47
     Pokémon
    0.46
     reimag
    0.46
     keychain
    0.46
     Photoshop
    0.45
     PCIe
    0.45
     Airbnb
    0.45
    Activations Density 0.016%

    No Known Activations