© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16327
    Prev
    Next
    INDEX
    Explanations

    chain or chains

    np_acts-logits-general · gemini-2.5-flash-lite

    artificial general intelligence and humanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iorum
    0.48
    Geb
    0.42
    或许
    0.42
    基础设施
    0.42
    ARDS
    0.41
    𝚍
    0.41
    ब्रिट
    0.40
    дм
    0.40
     அவற்ற
    0.40
     Geb
    0.38
    POSITIVE LOGITS
    牟
    0.44
     chain
    0.38
     يتم
    0.38
     chains
    0.38
     subgoal
    0.38
     chan
    0.37
     vf
    0.37
     tycker
    0.37
     চেয়ে
    0.37
     ehm
    0.37
    Activations Density 0.008%

    No Known Activations