© 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. 41-GEMMASCOPE-2-RES-262K
    7. 63726
    Prev
    Next
    INDEX
    Explanations

    configuration tags Name

    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_all/layer_41_width_262k_l0_big
    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
    дото
    0.43
     perplex
    0.38
     mengambil
    0.35
    udarstven
    0.34
     Contador
    0.33
     위
    0.33
    策划
    0.33
     décrites
    0.33
     Quark
    0.32
     Comet
    0.32
    POSITIVE LOGITS
    orgh
    0.43
     Before
    0.42
    velocityY
    0.41
     ન
    0.41
     categorie
    0.41
     BEFORE
    0.40
     map
    0.39
    枫
    0.39
     maps
    0.38
     category
    0.38
    Activations Density 0.001%

    No Known Activations