© 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. 10107
    Prev
    Next
    INDEX
    Explanations

    that we/you

    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
    ↵↵
    0.52
     Initialization
    0.45
    ↵↵↵↵
    0.44
     r
    0.44
     n
    0.43
     rumin
    0.43
     analges
    0.42
    ↵
    0.42
     handkerchief
    0.42
     decoy
    0.40
    POSITIVE LOGITS
     we
    0.57
     أنه
    0.57
     there
    0.55
    there
    0.55
     bahwa
    0.52
     rằng
    0.52
    THERE
    0.51
     أنّ
    0.51
     he
    0.50
    это
    0.50
    Activations Density 0.045%

    No Known Activations