© 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. 82613
    Prev
    Next
    INDEX
    Explanations

    largely overlooked or dismissed

    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
     improve
    0.55
     updateConfirm
    0.52
     thrombo
    0.52
     nourish
    0.51
     optimise
    0.50
    →</
    0.50
     metabol
    0.49
     mannit
    0.49
     osmotic
    0.49
     hardworking
    0.49
    POSITIVE LOGITS
    ت
    0.60
    ا
    0.59
    to
    0.58
    т
    0.57
    V
    0.56
    o
    0.55
    .
    0.55
    at
    0.53
    AT
    0.51
    Kre
    0.51
    Activations Density 0.004%

    No Known Activations