© 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. 47651
    Prev
    Next
    INDEX
    Explanations

    preparing for the next word

    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
     ammon
    0.45
     unhealthy
    0.44
     sway
    0.43
    牛奶
    0.42
     tuber
    0.41
    ⊡
    0.41
     amplification
    0.40
     anthem
    0.40
     earning
    0.39
    Ἥ
    0.39
    POSITIVE LOGITS
    予以
    0.46
    ađ
    0.43
     Gujar
    0.42
    gw
    0.42
     إلى
    0.40
     Various
    0.40
     ถึง
    0.39
    rafo
    0.39
     Adem
    0.39
    പരമായ
    0.39
    Activations Density 0.000%

    No Known Activations