© 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. 67324
    Prev
    Next
    INDEX
    Explanations

    river, dam, water

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

    river and its flow

    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
    proguard
    0.53
     السعودي
    0.51
     বিদ্ব
    0.51
     العالمي
    0.50
     cancé
    0.48
     tumeur
    0.48
     पठान
    0.48
    膻
    0.48
     बुरे
    0.47
    黟
    0.47
    POSITIVE LOGITS
     river
    1.81
    river
    1.47
     River
    1.45
     RIVER
    1.41
     नदी
    1.39
     riverside
    1.37
    河
    1.37
     upstream
    1.36
    River
    1.34
     downstream
    1.33
    Activations Density 0.303%

    No Known Activations