© 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. 11355
    Prev
    Next
    INDEX
    Explanations

    aware of someone or something

    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
    CameraOpened
    0.48
     Emil
    0.43
    routingHeader
    0.41
     eğer
    0.40
     אם
    0.38
    若是
    0.38
     चुनें
    0.38
    !<
    0.37
     निर्देशों
    0.37
    //#
    0.37
    POSITIVE LOGITS
     Vaux
    0.44
     remplacer
    0.42
     extinct
    0.40
    Belarus
    0.40
     devolution
    0.40
    代替
    0.39
     polio
    0.39
     descent
    0.39
     fission
    0.38
    Deletion
    0.38
    Activations Density 0.001%

    No Known Activations