© 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. 40839
    Prev
    Next
    INDEX
    Explanations

    proper nouns and concepts

    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
    Jaeger
    0.48
    ALL
    0.43
     Dhoni
    0.43
     (\%)
    0.41
    𝟭
    0.41
    Advisor
    0.40
     pleg
    0.40
     Jaguar
    0.39
    Nope
    0.39
     fatta
    0.39
    POSITIVE LOGITS
    ამართ
    0.49
    ห
    0.43
    蟄
    0.43
    ഴ്ച
    0.42
     uruch
    0.41
    竝
    0.41
    งาน
    0.40
    奖
    0.40
    കം
    0.40
     সঙ্ক
    0.40
    Activations Density 0.007%

    No Known Activations