© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17440
    Prev
    Next
    INDEX
    Explanations

    listen or listener

    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
     squre
    0.43
     SupCt
    0.42
     bhavati
    0.42
     záp
    0.42
     Sereth
    0.42
    鄕
    0.42
     CtApp
    0.42
    國民
    0.42
     Старки
    0.41
    벡
    0.41
    POSITIVE LOGITS
    торая
    0.44
     которая
    0.43
     colors
    0.42
    िक
    0.42
    max
    0.42
    ح
    0.42
    ங்க
    0.41
     fluids
    0.41
     modeled
    0.41
     آسیب
    0.41
    Activations Density 0.008%

    No Known Activations