© 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. 43049
    Prev
    Next
    INDEX
    Explanations

    flanked by or along

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

    water, food, energy, fertilizer

    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
     गंगा
    0.44
    大学生
    0.43
    长江
    0.42
    تمي
    0.39
    गंगा
    0.37
    rVert
    0.37
     ⿰
    0.37
    流水
    0.36
    辋
    0.36
     напи
    0.35
    POSITIVE LOGITS
     Solids
    0.52
     sediments
    0.47
     solids
    0.46
     ashore
    0.45
     insoluble
    0.43
     solutes
    0.41
     shore
    0.40
     salad
    0.39
     evaporation
    0.39
     stone
    0.38
    Activations Density 0.127%

    No Known Activations