© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6007
    Prev
    Next
    INDEX
    Explanations

    stones and rocks

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

    stones and rocks

    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_53_width_65k_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
     बजाज
    0.46
    裆
    0.42
    सर्जन
    0.39
    骋
    0.39
     शुक्ल
    0.39
    র্ধ্ব
    0.39
    騁
    0.39
     Meesho
    0.38
     मच्छर
    0.38
     вакци
    0.38
    POSITIVE LOGITS
     stones
    4.09
     stone
    3.78
    石头
    3.53
     rocks
    3.52
    石頭
    3.34
     Stones
    3.33
    石
    3.33
     piedras
    3.20
     камень
    3.17
    stones
    3.14
    Activations Density 0.258%

    No Known Activations