© 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. 31-GEMMASCOPE-2-RES-262K
    7. 203628
    Prev
    Next
    INDEX
    Explanations

    drawing shapes and instructions

    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
     violated
    0.48
     violates
    0.47
     iu
    0.46
     violate
    0.46
    ר
    0.44
    ূতন
    0.43
    adian
    0.43
     permissible
    0.42
     pertain
    0.42
    adow
    0.42
    POSITIVE LOGITS
    Responsible
    0.48
    Walking
    0.48
    Citizens
    0.46
    Taxi
    0.44
    Additionally
    0.44
    Conv
    0.43
    Boy
    0.43
    飧
    0.43
    Cyber
    0.42
    Turb
    0.42
    Activations Density 0.007%

    No Known Activations