© 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-16K
    7. 2087
    Prev
    Next
    INDEX
    Explanations

    user queries for information or tasks

    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_16k_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
     столи
    0.21
    ido
    0.20
     মানিক
    0.20
    Ă
    0.20
    ia
    0.19
     очередной
    0.19
     સહિત
    0.19
     पढ़ेंः
    0.19
    celikle
    0.19
    stö
    0.19
    POSITIVE LOGITS
     (>
    0.23
     a
    0.23
     cabelo
    0.22
     dispersive
    0.22
     network
    0.22
     conversa
    0.22
     neuromuscular
    0.22
     perceptual
    0.22
     vessel
    0.21
     dielectric
    0.21
    Activations Density 1.199%

    No Known Activations