© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11904
    Prev
    Next
    INDEX
    Explanations

    list items separated by commas

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

    listing abstract qualities

    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_262k_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
     হ্
    0.42
    ौदा
    0.41
     மட்டுமே
    0.37
    ufthansa
    0.37
    ដែលអាច
    0.37
     மட்டும்
    0.36
    রাষ্ট্রম
    0.36
     }=
    0.36
     aigus
    0.36
     byrow
    0.35
    POSITIVE LOGITS
    、
    1.33
    ፣
    1.14
    ၊
    1.10
     、
    1.09
    ,
    1.06
    ،
    1.05
    ﹑
    0.94
     ,
    0.92
    ､
    0.92
     ፣
    0.90
    Activations Density 0.342%

    No Known Activations