© 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. 44907
    Prev
    Next
    INDEX
    Explanations

    well-drained soil

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

    adjective describing 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
    하였
    0.47
     Constantinople
    0.44
     ‘
    0.43
     انشاء
    0.42
     occasional
    0.42
     declining
    0.41
     Christian
    0.41
     enkele
    0.41
     الذين
    0.41
     Zimbabwe
    0.40
    POSITIVE LOGITS
    ⚠️
    0.51
    滞
    0.49
    里
    0.47
    它
    0.47
    टेज
    0.47
    НА
    0.46
    thirsty
    0.46
    事故
    0.46
    众
    0.46
    疲
    0.46
    Activations Density 0.001%

    No Known Activations