© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23139
    Prev
    Next
    INDEX
    Explanations

    fountain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    铐
    0.46
     stripes
    0.43
     omfatt
    0.40
     robber
    0.40
    ْد
    0.39
    सनीय
    0.39
    レタン
    0.39
     setIsLoading
    0.39
    ភាព
    0.38
     बल्लेबाजी
    0.38
    POSITIVE LOGITS
     fountain
    1.79
     fountains
    1.70
     Fountain
    1.55
    ⛲
    1.27
     springs
    1.17
    泉
    1.12
     fonte
    1.07
    水源
    1.07
     water
    1.05
     fuente
    1.05
    Activations Density 0.009%

    No Known Activations