© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 21149
    Prev
    Next
    INDEX
    Explanations

    influenced by factors

    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_65k_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
     intereses
    0.53
     olahraga
    0.51
    叻
    0.46
     vieux
    0.46
     segítség
    0.46
     ciencia
    0.45
     ресурс
    0.45
    िप
    0.45
     старосног
    0.45
     adaptación
    0.45
    POSITIVE LOGITS
    [
    0.52
    (
    0.48
    {
    0.44
    </i>
    0.42
     Ngh
    0.42
    CHU
    0.42
    …
    0.42
     thoughts
    0.41
    pH
    0.41
    ありました
    0.41
    Activations Density 0.025%

    No Known Activations