© 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. 90290
    Prev
    Next
    INDEX
    Explanations

    Robb Stark, hull, gradients, prime

    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
     smells
    0.52
     penyebab
    0.50
    綃
    0.48
    我们
    0.46
     startTime
    0.46
     defectos
    0.46
     detalles
    0.46
     exons
    0.46
     smelled
    0.46
     chromosomes
    0.45
    POSITIVE LOGITS
    ove
    0.43
    とな
    0.43
    em
    0.43
    奮
    0.43
    og
    0.43
    craft
    0.42
    wait
    0.42
    prime
    0.41
    ot
    0.41
    سین
    0.41
    Activations Density 0.001%

    No Known Activations