© 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. 6251
    Prev
    Next
    INDEX
    Explanations

    has/have/are + descriptor

    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
    colare
    0.28
    ški
    0.27
     _{
    0.26
     که
    0.26
     coaction
    0.26
     কমপক্ষে
    0.26
    Subsec
    0.25
     присут
    0.25
    ">⁢</
    0.25
    avoir
    0.24
    POSITIVE LOGITS
     sooo
    0.31
     never
    0.31
     forskjellige
    0.31
     récemment
    0.31
     devenit
    0.30
     różnych
    0.30
     deviennent
    0.29
     forskellige
    0.29
     divent
    0.28
     lately
    0.27
    Activations Density 0.061%

    No Known Activations