© 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. 13942
    Prev
    Next
    INDEX
    Explanations

    concrete objects listed

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

    components arranged together

    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
    ته
    0.48
     dată
    0.48
    جنة
    0.48
    晧
    0.47
    ڈر
    0.46
    Downloads
    0.45
    釹
    0.45
    瓠
    0.45
    క్కు
    0.44
    物
    0.44
    POSITIVE LOGITS
     clustered
    0.80
     einzel
    0.79
     რომლებიც
    0.77
     которые
    0.74
     individually
    0.73
     jotka
    0.73
     collectively
    0.71
     themselves
    0.70
    clust
    0.70
     якія
    0.69
    Activations Density 0.162%

    No Known Activations